Intelligent detection system and method for precision forging punch-formed motor gear

Abstract

The invention discloses an intelligent detection system and method for a precision forging punch-formed motor gear, and relates to the technical field of intelligent detection of punch-formed gears. Comprising an intelligent punching machine, a data acquisition unit, an intelligent analysis unit, a processing execution unit and an early warning unit. In order to solve the problems of lagging of real-time monitoring and feedback, indefinite defect evaluation standard, insufficient defect repairing and adjusting capability and the like in the prior art, a system is combined with various technologies such as hydraulic monitoring, temperature monitoring, image recognition, laser scanning and the like, so that the whole-process real-time monitoring of the precision forging stamping gear is realized; through a high-precision sensor and an advanced image analysis algorithm, cracks, bubbles, recesses and other defects on the gear can be accurately recognized, and an automatic processing decision is made according to the severity of the defects. Compared with a traditional manual detection mode, the system has the advantages that the detection precision is greatly improved, personal errors are reduced, meanwhile, the labor cost is reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent detection of precision forging and stamping formed gears, and specifically to an intelligent detection system and method for motor gears formed by precision forging and stamping. Background Technique

[0002] Motor gears formed by precision forging and stamping are widely used in fields such as automobiles, power tools, and smart homes. Since their manufacturing process involves high-temperature plastic deformation and stamping forming, the dimensional accuracy, tooth profile integrity, and internal material defects of the gears are crucial for their service life and transmission performance. Traditional detection methods mainly rely on manual visual inspection, vernier calipers, or coordinate measuring machines for dimensional measurement, but these methods are inefficient, easily affected by human factors, and difficult to comprehensively detect the microscopic defects of gears. With the development of intelligent manufacturing, intelligent detection systems based on technologies such as computer vision, laser scanning, and ultrasonic detection have gradually been applied to the quality detection of motor gears to improve detection accuracy and efficiency and achieve automated production quality control;

[0003] The current motor gear detection system still has certain limitations; on the one hand, traditional stamping equipment lacks intelligent monitoring capabilities and cannot collect and analyze the operating states of key components (such as hydraulic rods, heating systems, stamping dies) in real time. On the other hand, traditional detection methods usually cannot quantitatively evaluate the severity of cracks, bubbles, and depressions, and cannot automatically adjust stamping parameters or perform secondary processing. Summary of the Invention

[0004] The purpose of the present invention is to solve the above-mentioned existing problems and propose an intelligent detection system and method for motor gears formed by precision forging and stamping.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] In a first aspect, the present invention provides an intelligent detection system for motor gears formed by precision forging and stamping, including: an intelligent stamping machine and an intelligent analysis unit;

[0007] The intelligent stamping machine includes a lower stamping body, an upper stamping body, a heating movable arm, a first hydraulic rod, a second hydraulic rod, a third hydraulic rod, a fourth hydraulic rod, an infrared ultra-clear camera, a first stamping gear die, a second stamping gear die, an electric heating copper tube, an LED fill light, and a precision forging and stamping gear blank; wherein, the lower stamping body and the upper stamping body are connected by the first hydraulic rod, the second hydraulic rod, the third hydraulic rod, and the fourth hydraulic rod; the heating movable arm and the first stamping gear die are installed on the lower stamping body; the infrared ultra-clear camera, the second stamping gear die, and the LED fill light are installed on the upper stamping body; the electric heating copper tube is installed on the heating movable arm; the precision forging and stamping gear blank is placed on the stamping gear die;

[0008] The process of the intelligent analysis unit for detecting the motor gear formed by precision forging and stamping is as follows:

[0009] Intelligently detect the rough gear blank after precision forging and stamping: Identify cracks: Calculate the gradient value of each pixel to obtain the horizontal gradient G x (x,y) and the vertical gradient G y (x,y), then calculate the magnitude of the gradient to obtain the gradient magnitude G(x,y), and calculate the gradient direction to obtain the gradient direction θ(x,y); Identify bubbles: Through the parametric equation of a circle, perform accumulation to form an accumulator; For each edge point, calculate the corresponding center coordinates and radius; Then, according to the calculated center coordinates (a,b) and radius value r, count the number of occurrences, and map with the size and quantity of the circle to obtain the bubble coefficient BC; Identify depressions, compare the obtained depression contour with the preset standard contour. If there is a depression, analyze according to the area size of the depression area, the perimeter and circularity, rectangularity, and aspect ratio of the depression contour to obtain the depression coefficient δZ.

[0010] As a preferred embodiment of the present invention, it further includes a data acquisition unit, a processing and execution unit, and an early warning unit;

[0011] The data acquisition unit is used to monitor and collect the operation data, environmental data, and status information of each component in the intelligent stamping machine in real time; Collect the operation status data of the hydraulic rod, heating movable arm, and stamping die components in real time, including displacement, pressure, and temperature data; Monitor the environmental conditions around the equipment; Capture image data during the stamping process through an infrared ultra-clear camera and an LED fill light; Record the power consumption of the electric heating copper tube and the overall energy efficiency data of the equipment; Transmit the collected data to the intelligent analysis unit through the network for further processing;

[0012] The processing and execution unit performs corresponding operations according to the detection results of the intelligent analysis unit; When it detects that the hydraulic pressure, temperature, or gear size exceeds the preset standard, the processing and execution unit adjusts the stamping machine parameters; When it detects that there are defects in the gear, the processing and execution unit takes different measures according to the degree of the defect: Repair the slightly defective gear and detect it again; For gears with more serious or severe defects, they are directly removed;

[0013] The early warning unit is responsible for issuing an alarm when an abnormal situation is detected and notifying the management personnel to intervene; If the data acquisition unit monitors that the hydraulic pressure exceeds the safe range, the heating temperature is abnormal, or the intelligent analysis unit detects that there are serious crack, bubble, and depression defects in the gear, the early warning unit immediately triggers the alarm mechanism and provides detailed abnormal information.

[0014] As a preferred embodiment of the present invention, the specific process for detecting the hydraulic system is as follows:

[0015] Collect the real-time pressure and displacement data of the hydraulic rod through a hydraulic sensor; compare the collected real-time data with a preset interval. If the collected pressure exceeds the preset threshold range, a warning is triggered; if the displacement of the hydraulic rod exceeds the preset range, it means a mechanical failure or an abnormality in the hydraulic system, and a warning is triggered by the early warning unit.

[0016] As a preferred embodiment of the present invention, the specific process of detecting the heating system is as follows:

[0017] Install a temperature sensor on the electric heating copper pipe to monitor the temperature in real time; compare the real-time temperature with a preset temperature interval. If the temperature exceeds the preset temperature interval, corresponding control instructions are generated, and the processing and execution unit stops the heating of the movable arm to avoid overheating and damaging the equipment.

[0018] As a preferred embodiment of the present invention, the specific process of detecting the precision forging and stamping gear blank is as follows:

[0019] Real-time monitor the offset and size of the gear blank through image recognition and laser scanning technologies; compare the data of image recognition and laser scanning with preset standard values; if the offset or size exceeds the preset standard range, corresponding control instructions are generated, and the processing and execution unit adjusts the parameters of the stamping machine or notifies the operator to intervene.

[0020] As a preferred embodiment of the present invention, the specific process of crack identification is as follows:

[0021] Identify the intensity change of the edges in the image by calculating the gradients of the image in the horizontal and vertical directions, and calculate the gradient value of each pixel: For each pixel point I(x,y), extract a 3x3 neighborhood, denoted as I(x - 1,y - 1) to I(x + 1,y + 1), by the formula: Get the horizontal gradient G x (x,y) and the vertical gradient G y (x,y), where S x (x,y) and S y (x,y) are the horizontal and vertical Sobel operators respectively; then through the obtained horizontal gradient G x (x,y) and the vertical gradient G y (x,y), calculate the magnitude and direction of the gradient: By the formula: Output the gradient magnitude G(x,y);

[0022] θ(x,y) = atan2(G x (x,y), G y (x,y)) outputs the gradient direction θ(x,y), where atan2 is a function for calculating radians.

[0023] As a preferred embodiment of the present invention, the specific process of identifying bubbles is as follows:

[0024] Convert the detected edge points in the Hough space; through the parametric equation of the circle, perform accumulation to form an accumulator; for each edge point, calculate its corresponding center coordinates and radius; if the center coordinates are (a, b) and the radius is r, the calculation is as follows: a = xi - rcos(θ1), b = yi - rsin(θ1), where θ1 is an angle parameter; according to the calculated center coordinates (a, b) and radius value r, count the number of occurrences; if the voting number of some centers exceeds the threshold and the size and position of the circle meet the expected characteristics of the bubble, the circular area is identified as a bubble; then, according to the size of the circle, map the quantity to obtain the bubble coefficient; if N bubbles are detected in the image, and the center coordinates of each bubble are (a i1 , b i1 ), and the radius is r i1 , where i1 ∈ [1, N], then the mapping formula of the bubble coefficient is: Output the bubble coefficient BC, where N is the number of detected bubbles, r i1 is the radius of the i1-th bubble, and ω(r i1 ) is a weight function related to the bubble size.

[0025] As a preferred embodiment of the present invention, the specific process of identifying depressions is as follows:

[0026] Use a contour extraction algorithm to obtain the contour of the depression; compare the obtained contour of the depression with a preset standard contour to check for the existence of depressions or protrusions. If a depression exists, calculate the area size of the depression area, and analyze the perimeter, circularity, rectangularity, and aspect ratio of the depression contour:

[0027] Output the depression coefficient δZ through the weighted average formula δZ = A1×o1 + P1×o2 + (1 - Y1)×o3 + (1 - R1)×o4 + AR×o5. A1 is the depression area, P1 is the contour perimeter, Y1 is the circularity, and Y1 = 4πA1 / P 2 , when Y1 is close to 1, it indicates that the depression is close to circular and is caused by uniform stress. When Y1 is less than 1, it indicates that the depression shape is irregular and is caused by mold problems or stamping defects. R1 is the rectangularity, and R1 = A1 / (L1×W1), where L1 and W1 are the length and width of the minimum circumscribed rectangle of the depression area. When the rectangularity is closer to 1, it indicates that the depression is close to rectangular. AR is the aspect ratio, AR = L1 / W1; o1, o2, o3, o4, and o5 are all preset weight factors, and o1 + o2 + o3 + o4 + o5 = 1.

[0028] In a second aspect, the present invention provides an intelligent detection method for precision forging and stamping motor gears, comprising:

[0029] Step 1: Real-time monitoring of the pressure, temperature, and displacement data of the hydraulic rod, heating arm, and key parts of the stamping die, and collection of stamping process images through infrared cameras and LED fill lights

[0030] Step 2: Monitor the equipment status, determine whether the pressure and temperature are out of limit, and adjust the stamping parameters; detect the offset and size of the gear blank through image recognition and laser scanning, and analyze the cracks, bubbles, and concave defects of the gear after stamping;

[0031] Step 3: Calculate the crack coefficient, bubble coefficient and dent coefficient for the detected defects; Crack detection is based on image gradient analysis to determine the length and depth of the crack and evaluate its impact level; Bubble detection uses the Hough transform method to identify circular defects and map the bubble coefficient by size and number; Depression detection is based on contour analysis to calculate the depression area, perimeter, circularity, rectangularity and aspect ratio, and finally output the depression coefficient and divide the impact level;

[0032] Step 4: If it is a minor defect, no treatment is required. If it is a moderate defect, repair it. If it is a serious defect or above, the gear will be directly eliminated and an early warning will be triggered.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. Compared with the existing manual detection or single sensor detection technology, the present invention integrates infrared ultra-clear cameras, laser scanning technology and intelligent image recognition algorithms to achieve high-precision automatic detection of gear defects; the system can capture the morphological features of gears in real time, and accurately identify defects such as cracks, bubbles, and dents through algorithms such as gradient analysis, Hough transform, and contour matching. At the same time, it automatically classifies according to preset standards to ensure the accuracy and consistency of the detection results, reduce human errors, and improve product quality.

[0035] 2. The present invention can not only detect defects in precision forged stamped gears, but also adjust stamping parameters in real time through the processing execution unit to optimize the production process; when the system finds an abnormality, it can automatically adjust the stamping pressure, temperature or mold position to avoid the occurrence of continuous defects; at the same time, for medium and above level defects, the system can automatically perform repair or removal operations, and link the early warning unit to remind maintenance personnel, greatly improving production efficiency and reducing the scrap rate and manual intervention costs caused by defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0037] Figure 1 is the principle block diagram of the present invention;

[0038] Figure 2 is the method step diagram of the present invention;

[0039] Figure 3 is the schematic diagram of the intelligent stamping machine of the present invention Figure 1 ;

[0040] Figure 4 is the schematic diagram of the intelligent stamping machine of the present invention Figure 2 ;

[0041] Figure 5 is the schematic diagram of the intelligent stamping machine of the present invention Figure 3 .

[0042] Description of the drawings: 1. Lower stamping body; 2. Heating movable arm; 3. First hydraulic rod; 4. Infrared ultra-clear camera; 5. Upper stamping body; 6. First stamping gear die; 7. Electric heating copper tube; 8. LED fill light; 9. Precision forging stamping gear blank; 10. Second stamping gear die; 11. Second hydraulic rod; 12. Third hydraulic rod; 13. Fourth hydraulic rod. Detailed implementation manners

[0043] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention. It should be understood that the terms "including" and "comprising" used in the specification and claims of this disclosure indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0044] It should also be understood that the terms used in this disclosure specification are only for the purpose of describing specific embodiments, and are not intended to limit this disclosure. As used in the specification and claims of this disclosure, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in the specification and claims of this disclosure refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0045] Example 1:

[0046] Please refer to Figure 1As shown in the figure, an intelligent detection system for motor gears formed by precision forging and stamping includes: an intelligent stamping machine, a data acquisition unit, an intelligent analysis unit, a processing and execution unit, and a warning unit;

[0047] Please refer to Figure 3 , 4 , as shown in Figure 5, the intelligent stamping machine includes: a lower stamping body 1, an upper stamping body 5, a heating movable arm 2, a first hydraulic rod 3, a second hydraulic rod 11, a third hydraulic rod 12, a fourth hydraulic rod 13, an infrared ultra-clear camera 4, a stamping gear die 6, a stamping gear die 10, an electric heating copper tube 7, an LED fill light 8, and a precision forging and stamping gear blank 9; among them, the lower stamping body 1 and the upper stamping body 5 are connected by the hydraulic rods 3, 11, 12, and 13; the heating movable arm 2 and the stamping gear die 6 are installed on the lower stamping body 1; the infrared ultra-clear camera 4, the stamping gear die 10, and the LED fill light 8 are installed on the upper stamping body 5; the electric heating copper tube 7 is installed on the heating movable arm 2; the precision forging and stamping gear blank 9 is placed on the stamping gear die 6;

[0048] The data acquisition unit is used to monitor and collect the operation data, environmental data, and status information of each component in the intelligent stamping machine in real time; collect the operation status data of components such as hydraulic rods, heating movable arms, and stamping dies in real time, including data such as displacement, pressure, and temperature; monitor the environmental conditions around the equipment, such as temperature, humidity, and light intensity, which may affect the quality and efficiency of the stamping process; capture image data during the stamping process through the infrared ultra-clear camera 4 and the LED fill light 8 to help detect the condition of the stamping gear die and the quality of the precision forging and stamping gear blank; record the power consumption of the electric heating copper tube and the overall energy efficiency data of the equipment; finally, transmit the collected data to the intelligent analysis unit through the network for further processing; the intelligent analysis unit is used to detect the motor gears formed by precision forging and stamping. The specific process is as follows:

[0049] First, monitor the intelligent stamping machine itself. Specifically:

[0050] Monitor the hydraulic system. Collect the real-time pressure and displacement data of the hydraulic rods through hydraulic sensors; compare the collected real-time data with the preset interval. If the collected pressure exceeds the preset threshold range (such as higher than 1500 bar or lower than 1000 bar), a warning is triggered; if the displacement of the hydraulic rod exceeds the preset range (such as more than 50 mm), it may mean mechanical failure or abnormal hydraulic system, and a warning is triggered by the warning unit;

[0051] Monitor the heating system by installing temperature sensors on the electric heating copper pipes to monitor the temperature in real time; compare the real-time temperature with the preset temperature range. If the temperature exceeds the preset temperature range, generate corresponding control instructions, and the processing and execution unit stops the heating arm from working to avoid overheating and damaging the equipment;

[0052] Monitor the precision forging and stamping gear blanks by using image recognition and laser scanning technologies to monitor the offset and size of the gear blanks in real time; compare the data from image recognition and laser scanning with the preset standard values; if the offset or size exceeds the preset standard range, generate corresponding control instructions, and the processing and execution unit adjusts the stamping machine parameters or notifies the operator to intervene;

[0053] Secondly, conduct intelligent inspection on the precision forging gear blanks after stamping, specifically as follows:

[0054] Capture the image data of the precision forging gear blanks after stamping through the infrared ultra-clear camera 4 and the LED fill light 8 carried by the intelligent stamping machine, and conduct feature analysis on the corresponding image data of the precision forging gear blanks: (features include defects such as cracks, bubbles, and depressions);

[0055] Identify cracks: By calculating the gradients of the image in the horizontal and vertical directions to identify the intensity changes of the edges in the image. (Cracks usually form significant brightness changes in the image. Therefore, perform convolution operations in the horizontal and vertical directions of the image respectively to extract the regions with significant brightness changes, which are the regions where cracks may exist.) Calculate the gradient value of each pixel: For each pixel point I(x,y), extract a 3x3 neighborhood, denoted as I(x - 1,y - 1) to I(x + 1,y + 1), and use the formula: Get the horizontal gradient G x (x,y) and the vertical gradient G y (x,y), where S x (x,y) and S y (x,y) are the horizontal and vertical Sobel operators respectively; then through the obtained horizontal gradient G x (x,y) and the vertical gradient G y (x,y), calculate the magnitude and direction of the gradient: Through the formula: Output the gradient magnitude G(x,y);

[0056] θ(x,y) = atan2(G x (x,y),G y(x, y)) outputs the gradient direction θ(x, y), where atan2 is a function that calculates radians and returns the angle of the gradient direction; compare the gradient magnitude G(x, y) with two preset high and low thresholds. If the gradient magnitude G(x, y) is not between the two preset high and low thresholds, determine whether the edge is significant and whether it is a crack; then map the corresponding crack coefficient according to the crack length: assume a crack length of 5 mm and a depth of 0.8 mm. The system may classify it as a medium crack, and then the processing execution unit notifies the operator to fill it; if the crack is 10 mm long and 1.5 mm deep, it is regarded as a severe crack. The processing execution unit notifies the operator to handle it and replaces the stamping gear die 6 and the stamping gear die 10;

[0057] Identify the bubbles: Convert the detected edge points in the Hough space; through the parametric equation of the circle, perform accumulation to form an accumulator; for each edge point, calculate its possible corresponding center coordinates and radius; if the center coordinates are (a, b) and the radius is r, the calculation is: a = xi - rcos(θ1), b = yi - rsin(θ1), where θ1 is an angular parameter representing the position of each point on the circle relative to the center of the circle; according to the calculated center coordinates (a, b) and radius value r, count the number of occurrences; if the vote count of some centers exceeds the threshold and the size and position of the circle meet the expected characteristics of the bubbles, these circular regions will be identified as bubbles; then map the quantity according to the size of the circle to obtain the bubble coefficient; if N bubbles are detected in the image, and the center coordinates of each bubble are (a i1 , b i1 ), and the radius is r i1 , where i1 ∈ [1, N], then the mapping formula of the bubble coefficient is: Output the bubble coefficient BC, where N is the number of detected bubbles, r i1 is the radius of the i1-th bubble, and ω(r i1 ) is a weight function related to the size of the bubble. Usually, it can be set according to the size of the bubble; for example, larger bubbles may have a greater weight; compare the bubble coefficient BC with the preset instruction thresholds, which include BC1 and BC2, and BC1 < BC2. If BC1 ≤ BC < BC2, the processing execution unit notifies the operator to fill it. If BC ≥ BC2, the processing execution unit notifies the operator to handle it and replaces the stamping gear die 6 and the stamping gear die 10;

[0058] Identify the depression. Similarly, use the contour extraction algorithm to obtain the contour of the depression; compare the obtained contour of the depression with the preset standard contour to check for depressions or protrusions. If there is a depression, calculate the area of the depression area, and calculate the perimeter, circularity, rectangularity, and aspect ratio of the depression contour for analysis:

[0059] Output the depression coefficient δZ through the established formula: δZ = A1×o1 + P1×o2 + (1 - Y1)×o3 + (1 - R1)×o4 + AR×o5, where A1 is the depression area (the area of the depression area, the larger the area, the more severe the depression), P1 is the contour perimeter (the contour perimeter represents the edge length of the depression and is usually used in combination with the area to reflect the shape complexity of the depression), Y1 is the circularity, and Y1 = 4πA1 / P 2 , when Y1 is close to 1, it indicates that the depression is close to circular and may be caused by uniform stress. When Y1 is less than 1, it indicates that the depression shape is irregular and may be caused by mold problems or stamping defects. R1 is the rectangularity, and R1 = A1 / (L1×W1), where L1 and W1 are the length and width of the minimum circumscribed rectangle of the depression area. When the rectangularity is closer to 1, it indicates that the depression is closer to rectangular. AR is the aspect ratio, AR = L1 / W1. If the aspect ratio AR is greater than 1, the depression shape is slender and may be caused by uneven local pressure of the mold; o1, o2, o3, o4, and o5 are all preset weight factors; 1 - Y1 inversely represents the lower the circularity, the more irregular the depression shape, and the greater the impact on the gear; 1 - R1 inversely represents the lower the rectangularity, the more complex the shape, and the greater the impact. Then, according to the size of the depression coefficient δZ, divide the impact of the depression on the gear, and set 4 thresholds, namely AX1, AX2, AX3, and AX4, and AX1 < AX2 < AX3 < AX4; if δZ < AX1, the impact level is minor; if AX1 ≤ δZ < AX2, the impact level is medium; if AX2 ≤ δZ < AX3, the impact level is relatively severe; if δZ ≥ AX4, the impact level is severe; if there is no depression and there is a protrusion, the processing execution unit will apply pressure again and re-identify the depression;

[0060] When the processing execution unit receives an impact level of minor, the impact is small, which is a normal process error and does not affect use, so no processing is required; when the processing execution unit receives an impact level of medium, it affects the gear accuracy, needs to be monitored but does not affect short-term use, and is repaired, and the repaired gear is analyzed for depression; when the processing execution unit receives an impact levels of relatively severe and severe, it is directly removed, and the warning unit issues an alarm and notifies the operator for processing, and replaces the stamping gear mold 6 and stamping gear mold 10;

[0061] Example 2:

[0062] Please refer to Figure 2As shown in the figure, an intelligent detection method for precision forging and stamping of motor gears, the specific steps are as follows:

[0063] Step 1: The intelligent stamping machine is equipped with a data acquisition unit to monitor the operating status of key components (hydraulic rod, heating movable arm 2, stamping die, etc.) in real time, including data such as pressure, displacement, and temperature; at the same time, the infrared ultra-clear camera 4 and the LED fill light 8 are used to capture image data of the stamping process to monitor the quality of the gear blank; and record the energy consumption of the electric heating copper tube 7 and the equipment energy efficiency data, and transmit all the collected information to the intelligent analysis unit for processing;

[0064] Step 2: Detect the stamping machine itself and the motor gear formed by stamping; first, the system monitors the hydraulic system and the heating system to ensure that the pressure and temperature are within the preset range, and if it exceeds the threshold, an alarm is triggered or the parameters are adjusted; secondly, the system uses image recognition and laser scanning technology to analyze the offset and size of the gear blank, and if the deviation exceeds the standard range, an adjustment instruction is generated; after stamping, further identify the surface defects (cracks, bubbles, depressions, etc.) of the gear, and calculate the corresponding defect coefficient to quantify the impact of the defect on the gear quality;

[0065] Step 3: For the detected defects, calculate the crack coefficient, bubble coefficient, and depression coefficient; crack detection is based on image gradient analysis to judge the length and depth of the crack and evaluate its impact level; bubble detection uses the Hough transform method to identify circular defects and maps the bubble coefficient through size and quantity; depression detection is based on contour analysis to calculate the depression area, perimeter, circularity, rectangularity, and aspect ratio, and finally outputs the depression coefficient and divides the impact level (slight, medium, relatively serious, serious);

[0066] Step 4: The processing execution unit makes corresponding treatments according to the defect level. Slight defects do not affect use and do not need to be treated; medium defects affect the accuracy but can be repaired; relatively serious and above defects directly remove unqualified products and trigger the warning unit to notify the management personnel; if the depression detection finds protrusions, the system re-executes the pressure-bearing process for correction to ensure the stability of the gear quality; at the same time, if serious defects continuously occur, the system recommends replacing the stamping die to ensure the production quality.

[0067] The above disclosed preferred embodiments of the present invention are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor limit the invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the art in the technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent detection system for precision forging and stamping motor gears, comprising: Intelligent punching machine and intelligent analysis unit, characterized by: The intelligent punching machine comprises a punching lower body (1), a punching upper body (5), a heating movable arm (2), a hydraulic rod 1 (3), a hydraulic rod 2 (11), a hydraulic rod 3 (12), a hydraulic rod 4 (13), an infrared ultra-clear camera (4), a punching gear die 1 (6), a punching gear die 2 (10), an electric heating copper tube (7), an LED fill light (8) and a precision forging punching gear blank (9); the intelligent analysis unit is used to detect the precision forging punching motor gear in the following process: Intelligent detection of gear blanks after precision forging and stamping: Identification of cracks: Calculation of the gradient value of each pixel to obtain the horizontal gradient G x (x,y) and the vertical gradient G y (x, y), then calculate the gradient amplitude to obtain the gradient amplitude G(x, y), calculate the gradient direction to obtain the gradient direction θ(x, y); identify bubbles: accumulate through the parameterized circle equation to form an accumulator; for each edge point, calculate the corresponding center coordinates and radius; then count the number of occurrences based on the calculated center coordinates (a, b) and radius value r, and map them with the size and number of circles to obtain the bubble coefficient BC; identify depressions, compare the obtained depression contour with the preset standard contour for overlap, and if a depression exists, analyze the depression coefficient δZ based on the area size of the depression area, the perimeter of the depression contour, the circularity, rectangularity, and aspect ratio.

2. According to claim 1, the intelligent detection system for precision forging and stamping motor gears is characterized in that: The stamping lower body (1) is connected to the stamping upper body (5) via hydraulic rod one (3), hydraulic rod two (11), hydraulic rod three (12) and hydraulic rod four (13); the heating movable arm (2) and the stamping gear die one (6) are installed on the stamping lower body (1); the infrared ultra-clear camera (4), the stamping gear die two (10) and the LED fill light (8) are installed on the stamping upper body (5); the electric heating copper tube (7) is installed on the heating movable arm (2); the precision forging stamping gear blank (9) is placed on the stamping gear die one (6); It also includes a data acquisition unit, a processing execution unit and an early warning unit; The data acquisition unit is used to monitor and collect the operation data, environmental data and status information of each component in the intelligent stamping machine in real time; collect the operation status data of the hydraulic rod, the heating movable arm and the stamping die components in real time, including displacement, pressure and temperature data; monitor the environmental conditions around the equipment; capture the image data of the stamping process through the infrared ultra-clear camera (4) and the LED fill light (8); record the power consumption of the electric heating copper tube and the overall energy efficiency data of the equipment; transmit the collected data to the intelligent analysis unit through the network for further processing; The processing execution unit performs corresponding operations according to the detection results of the intelligent analysis unit; when it is detected that the hydraulic pressure, temperature or gear size exceeds the preset standard, the processing execution unit adjusts the parameters of the punching machine; when a gear defect is detected, the processing execution unit takes different measures according to the degree of the defect: repair the gear with minor defects and test it again; directly remove the gear with more serious or severe defects; The early warning unit is responsible for issuing an alarm when an abnormal situation is detected and notifying management personnel to intervene; if the data acquisition unit monitors that the hydraulic pressure exceeds the safety range, the heating temperature is abnormal, or the intelligent analysis unit detects serious cracks, bubbles and dents in the gears, the early warning unit immediately triggers the alarm mechanism and provides detailed abnormal information.

3. The intelligent detection system for precision forging and stamping motor gears according to claim 1 is characterized in that: The specific process of testing the hydraulic system is as follows: The real-time pressure and displacement data of the hydraulic rod are collected through the hydraulic sensor; the collected real-time data is compared with the preset interval. If the collected pressure exceeds the preset threshold range, a warning is triggered; if the displacement of the hydraulic rod exceeds the preset range, it means a mechanical failure or hydraulic system abnormality, and the early warning unit triggers a warning.

4. The intelligent detection system for precision forging and stamping motor gears according to claim 3 is characterized in that: The specific process of detecting the heating system is as follows: By installing a temperature sensor on the electric heating copper tube (7), the temperature is monitored in real time; the real-time temperature is compared with a preset temperature range, and if the temperature exceeds the preset temperature range, a corresponding control instruction is generated, and the processing execution unit stops the heating movable arm from working, thereby avoiding overheating and damaging the equipment.

5. The intelligent detection system for precision forging and stamping motor gears according to claim 4 is characterized in that: The specific process of testing the precision forged stamped gear blank is as follows: The offset and size of the gear blank are monitored in real time through image recognition and laser scanning technology; the data from image recognition and laser scanning are compared with the preset standard values; if the offset or size exceeds the preset standard range, a corresponding control instruction is generated, and the processing execution unit adjusts the stamping machine parameters or notifies the operator to intervene.

6. The intelligent detection system for precision forging and stamping motor gears according to claim 1 is characterized in that: The specific process of crack identification is as follows: By calculating the gradient of the image in the horizontal and vertical directions, we can identify the intensity change of the edge in the image and calculate the gradient value of each pixel: for each pixel point I(x,y), extract a 3x3 neighborhood, recorded as I(x-1,y-1) to I(x+1,y+1), according to the formula: Get the horizontal gradient G x (x,y) and the vertical gradient G y (x,y), S x (x,y) and S y (x, y) are the horizontal and vertical Sobel operators respectively; then the horizontal gradient G x (x,y) and the vertical gradient G y (x, y), calculate the magnitude and direction of the gradient: by the formula: Output gradient magnitude G(x,y); θ(x,y)=a tan2(G x (x,y),G y (x,y)) outputs the gradient direction θ(x,y), where atan2 is a function that calculates radians.

7. The intelligent detection system for precision forging and stamping motor gears according to claim 6 is characterized in that: The specific process of identifying bubbles is as follows: The detected edge points are transformed in Hough space; the equation of the parameterized circle is accumulated to form an accumulator; for each edge point, the corresponding circle center coordinates and radius are calculated; if the circle center coordinates are (a, b) and the radius is r, the calculation is: a = xi-rcos (θ1), b = yi-rsin (θ1), where θ1 is an angle parameter; according to the calculated circle center coordinates (a, b) and radius value r, the number of occurrences is counted; if the number of votes for some circle centers exceeds the threshold, and the size and position of the circle meet the expected characteristics of the bubble, the circular area is identified as a bubble; then the number is mapped according to the size of the circle to obtain the bubble coefficient; if N bubbles are detected in the image, the center coordinates of each bubble are (a i1 ,b i1 ), with a radius of r i1 , where i1∈[1,N], the mapping formula of the bubble coefficient is: Output bubble coefficient BC, where N is the number of bubbles detected, r i1 is the radius of the i1th bubble, ω(r i1 ) is a weight function related to the bubble size.

8. The intelligent detection system for precision forging and stamping motor gears according to claim 7 is characterized in that: The specific process of identifying the depression is as follows: Use the contour extraction algorithm to obtain the contour of the depression; compare the obtained contour of the depression with the preset standard contour to see if there is a depression or a bulge. If there is a depression, calculate the area of ​​the depression area, and calculate the perimeter, circularity, rectangularity, and aspect ratio of the depression contour for analysis: The concave coefficient δZ is output through the weighted average formula δZ=A1×o1+P1×o2+(1-Y1)×o3+(1-R1)×o4+AR×o5, where A1 is the concave area, P1 is the contour circumference, Y1 is the circularity, and Y1=4πA1 / P 2 When Y1 is close to 1, it means that the depression is close to a circle, which is caused by uniform force. When Y1 is less than 1, it means that the depression is irregular in shape, which is caused by mold problems or stamping defects. R1 is the rectangularity, and R1=A1 / (L1×W1). L1 and W1 are the length and width of the minimum circumscribed rectangle of the depression area. When the rectangularity is closer to 1, it means that the depression is close to a rectangle. AR is the aspect ratio, AR=L1 / W1; o1, o2, o3, o4 and o5 are all preset weight factors, o1+o2+o3+o4+o5=1.

9. An intelligent detection method for precision forging and stamping motor gears, characterized in that: An intelligent detection system for motor gears used to implement a precision forging and stamping process as described in any one of claims 1 to 8; comprising: Step 1: real-time monitoring of the pressure, temperature and displacement data of the hydraulic rod (1), the heating movable arm (2) and the key components of the stamping die, and collecting stamping process images through an ultra-clear infrared camera (4) and an LED fill light (8); Step 2: Monitor the equipment status, determine whether the pressure and temperature are out of limit, and adjust the stamping parameters; detect the offset and size of the gear blank through image recognition and laser scanning, and analyze the cracks, bubbles, and concave defects of the gear after stamping; Step 3: Calculate the crack coefficient, bubble coefficient and dent coefficient for the detected defects; Crack detection is based on image gradient analysis to determine the length and depth of the crack and evaluate its impact level; Bubble detection uses the Hough transform method to identify circular defects and map the bubble coefficient by size and number; Depression detection is based on contour analysis to calculate the depression area, perimeter, circularity, rectangularity and aspect ratio, and finally output the depression coefficient and divide the impact level; Step 4: If it is a minor defect, no treatment is required. If it is a moderate defect, repair it. If it is a serious defect or above, the gear will be directly eliminated and an early warning will be triggered.

Images