A system for real-time monitoring and data analysis of parameters in a forging process

Abstract

This invention relates to the field of industrial process monitoring technology, and particularly to a system for real-time monitoring and data analysis of parameters during forging. The system includes an acoustic judgment module, a mechanical parameter judgment module, a friction state judgment module, a cooling monitoring module, and a feedback adjustment module. The acoustic judgment module collects the type of acoustic signal. The mechanical parameter judgment module collects the stroke force signal and reaction force and generates a set of mechanical parameters when the acoustic signal meets preset conditions. The friction state judgment module determines the friction state type based on the coating coverage and inertial motion distance. The cooling monitoring module identifies and handles abnormal cooling areas during the cooling cycle. The feedback adjustment module adjusts the acoustic amplitude threshold or the stamping environment temperature based on the abnormal cooling conditions. This system, through dynamic monitoring of multiple parameters and abnormal feedback, achieves real-time data acquisition, state determination, and closed-loop control of the forging process, ensuring forming quality and process stability.

Description

Technical Field

[0001] This invention relates to the field of industrial process monitoring technology, and in particular to a system for real-time monitoring and data analysis of parameters during the forging process. Background Technology

[0002] Forging is a crucial method for the plastic forming of metallic materials, widely used in the automotive, aerospace, and energy equipment industries. The forging process involves multiple process parameters, including load, friction, temperature, and cooling. These factors are intricately coupled and have a decisive impact on the forming accuracy, microstructure, and lifespan of forgings. With the development of intelligent manufacturing, how to achieve real-time monitoring and dynamic control of key parameters during the forging process has become a core issue for improving product quality and reducing energy consumption.

[0003] In existing technologies, process monitoring often employs a single signal source, such as displacement-force curves, surface temperature fields, or impact acoustic signals, to assess the process status. However, a single parameter often fails to fully reflect the complex characteristics of forging and is prone to unreliable results due to noise interference, inaccurate monitoring windows, or detection lag. Furthermore, most monitoring methods remain at the post-event analysis level, lacking real-time and targeted adjustment mechanisms. Even in studies that have introduced multi-source data fusion, the coupling analysis between monitoring indicators is insufficient, and a stable closed-loop control mechanism has not yet been established.

[0004] Therefore, existing forging process monitoring systems are inadequate in terms of data integrity, anomaly identification accuracy, and feedback control capabilities. There is an urgent need to propose a system that can integrate multi-source monitoring information and has adaptive adjustment capabilities to achieve real-time monitoring and process optimization of the forging process.

[0005] Chinese Patent Publication No. CN120656006A discloses a method and system for monitoring the forging of shaft parts. The method includes acquiring feature values ​​of pixels in multiple channels of the HSV color space within a surface image of the formed shaft part, as well as the gradient direction angle of the pixels; determining the local consistency of the pixels; determining the weighted Euclidean distance between pixels; clustering all pixels according to the weighted Euclidean distance to obtain several clusters; determining the gradient saliency and the number of candidate corner points in the image region where the clusters are located; obtaining candidate corner points using the Harris corner detection algorithm based on the number of candidate corner points; and measuring the forging qualification of the shaft part according to the Euclidean distance between the candidate corner points.

[0006] Existing industrial process monitoring technologies rely on surface images of shaft parts after forming for feature extraction and corner analysis. The monitoring object is the static state after forming, lacking the capture of real-time mechanical parameters and friction state during the stroke. It is impossible to dynamically judge the displacement, inertial response and friction effects of the billet during the forming process, resulting in the inability to detect and correct processing deviations and local stress anomalies in a timely manner, making it difficult to ensure the overall forming quality and consistency of forgings. Summary of the Invention

[0007] To address this, the present invention provides a system for real-time monitoring and data analysis of parameters during the forging process. This system aims to overcome the problem of unstable quality caused by internal cracks in the billet that are difficult to detect during the forming process, by accurately acquiring key time points of the stroke and frictional movement distance.

[0008] To achieve the above objectives, the present invention provides a system for real-time monitoring and data analysis of parameters during the forging process, comprising: The acoustic judgment module is used to collect the punching sound signal when the upper die forming surface presses the blank during each stroke, and to determine the sound signal category to which the punching sound signal belongs, and output the sound signal judgment result. The mechanical parameter judgment module is connected to the acoustic judgment module. When the first acoustic signal category judgment result is obtained, the module collects the action time corresponding to the stroke force signal when the upper die forming surface of each stroke presses the blank, and stores the collected stroke force signal and its action time into the force signal set. The friction state determination module is connected to the acoustic determination module and the mechanical parameter determination module. When the second acoustic signal category determination result is obtained, the inertia height of the billet is calculated, and the inertia height is compared with a preset inertia height threshold to determine the category of friction state based on the inertia height comparison result. The cooling monitoring module is connected to the acoustic judgment module, the mechanical parameter judgment module and the friction state judgment module. It is used to determine whether there is a first abnormal cooling area on the surface of the billet that has not been shaken during the cooling cycle, and to determine whether there is a second abnormal cooling area after the shaking treatment when there is a first abnormal cooling area. The feedback adjustment module is connected to the cooling monitoring module and the acoustic judgment module. When the first abnormal cooling area is detected, the acoustic amplitude threshold corresponding to the stroke acoustic signal is linearly adjusted. When the second abnormal cooling area is detected, the stamping environment temperature is adjusted accordingly.

[0009] Furthermore, the acoustic judgment module includes a time stamping unit, a symmetrical sampling unit, and an acoustic signal acquisition unit; The time stamp unit is used to obtain the timestamp when the upper die forming surface contacts the blank in each stroke and record it as the first stamp time, and to obtain the timestamp when the slider moves to the bottom dead center and record it as the second stamp time; A symmetrical point-taking unit is used to obtain the time interval between the first marked time and the second marked time, and with the second marked time as the time starting point for symmetrical processing, to obtain the timestamp after the time interval from the time starting point and record it as the third marked time. The acoustic signal acquisition unit is connected to the time marking unit and the symmetrical sampling unit, and uses the time interval from the first marked time to the third marked time as the monitoring window for each stroke, and acquires the acoustic signal within the monitoring window.

[0010] Furthermore, the acoustic judgment module also includes an acoustic signal judgment unit; The sound signal judgment unit is used to acquire the sound signal, including sound amplitude and high frequency component, within the monitoring window, and to obtain the first sound signal result when the sound amplitude is greater than or equal to a preset sound amplitude threshold and the high frequency component is greater than or equal to a preset high frequency proportion threshold.

[0011] Furthermore, the mechanical parameter determination module includes a force acquisition unit and a reaction force detection unit; The force acquisition unit is used to acquire the stroke force signal of the slider in the monitoring window when the first sound signal result is obtained; The reaction force detection unit is connected to the force acquisition unit to obtain the reaction force of the stamping blank on the upper die forming surface after the second mark time, and the fourth mark time is when the reaction force in each stroke is returned to zero.

[0012] Furthermore, the reaction force detection unit includes an image acquisition subunit and a billet separation time detection subunit; The image acquisition subunit is used to acquire several connected images, including the upper die forming surface and the blank forming protrusion, at a fixed acquisition frequency when the slider moves from the bottom dead center to the top dead center in each stroke. The blank removal time detection subunit is connected to the image acquisition subunit and is used to mark the fourth time based on the several connected images when the coordinates of the upper mold forming surface and the blank forming protrusion in the vertical direction are inconsistent and the reaction force is zero.

[0013] Furthermore, the friction state determination module includes a spray volume detection unit and a distance calculation unit; The spray volume detection unit is used to acquire several spray images of the blank surface and the upper die forming surface at a fixed acquisition frequency when spraying graphite emulsion in each stroke, and to determine the coverage of graphite emulsion spraying based on the several spray images. The distance calculation unit is connected to the spray volume detection unit and is used to determine the frictional motion distance in the inertial motion distance under the graphite emulsion spray coverage.

[0014] Furthermore, the friction state determination module also includes a distance comparison unit; The distance comparison unit is connected to the spray volume detection unit and the distance calculation unit, and is used to compare the inertial motion distance with the preset inertial motion distance threshold to obtain the inertial motion distance comparison result and obtain the category to which the corresponding billet preliminary processing result belongs.

[0015] Furthermore, the cooling monitoring module includes a surface detection unit, an interference elimination unit, and a surface re-detection unit; The surface detection unit is used to determine, when the initial processing result of the first billet is obtained, whether the surface of the billet that has not been shaken during the cooling cycle is a first abnormal cooling area where there is no abnormal cooling area and the cooling rate is greater than a preset cooling threshold. An interference elimination unit, connected to the surface detection unit, is used to shake the billet when there is an abnormal cooling area. The surface re-detection unit, connected to the interference elimination unit, is used to determine whether there is a second abnormal cooling area on the surface of the billet after the shaking process, where the cooling rate is greater than a preset cooling threshold.

[0016] Furthermore, the feedback adjustment module includes a first feedback unit and a second feedback unit; The first feedback unit is used to adjust the threshold corresponding to the stroke acoustic signal when the abnormal cooling area is the first abnormal cooling area. The second feedback unit, connected to the first feedback unit, is used to adjust the stamping environment temperature when the abnormal cooling area is the second abnormal cooling area.

[0017] Furthermore, the first feedback unit includes a threshold adjustment subunit and a high-frequency adjustment subunit; The threshold adjustment subunit is used to linearly adjust the preset sound amplitude threshold in the acoustic judgment module according to the preset sound amplitude threshold adjustment ratio coefficient when the first abnormal cooling area is obtained. The high-frequency adjustment subunit, connected to the threshold adjustment subunit, is used to adjust the high-frequency proportion threshold by a fixed ratio when an abnormal temperature region still occurs after the preset sound amplitude threshold adjustment number is greater than the standard adjustment number.

[0018] Compared with existing technologies, the beneficial effects of this invention are as follows: by accurately acquiring the inertial motion distance of the slider during the stroke, and combining it with the graphite emulsion spray coverage and billet mass, the frictional motion distance is calculated, thereby achieving a quantitative determination of the displacement of the billet caused by friction; by determining the slider's rising speed and inertial displacement through a stroke monitoring window with a fixed time period, the frictional motion distance is distinguished from the inertial motion; the frictional motion distance can be used to classify the initial processing results of the billet, guiding the adjustment of the spray coverage and optimization of the cooling strategy; this method can accurately reflect the friction state, reduce the billet movement deviation caused by excessive friction, and improve forming accuracy; by separating inertial motion and frictional motion, quantitative analysis of frictional characteristics during the stroke is achieved, friction control measures are optimized, graphite emulsion spraying efficiency is improved, the incidence of surface defects is reduced, and reliable data is provided for subsequent cooling monitoring and feedback adjustment; the correlation between the frictional motion distance and the spray coverage and slider movement speed ensures the controllability of the processing process, improves the uniformity of the billet surface and processing consistency, enhances the stability and repeatability of the forging process, and achieves real-time evaluation and optimization of the friction-driven process.

[0019] Furthermore, it can accurately capture the acoustic vibrations generated by the contact between the die and the blank and the plastic deformation during the stroke, providing reliable data for mechanical parameter judgment, inertial motion analysis and coating amount optimization, and ensuring the controllability of the forming process.

[0020] Furthermore, quantitative analysis of the mechanical state during the stamping process is achieved, providing accurate quantitative data for subsequent friction determination, coating amount adjustment, and forming parameter optimization, ensuring force balance during blank stamping and stability during demolding. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the structure of the system for real-time monitoring and data analysis of parameters during the forging process according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the acoustic judgment module according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the friction state determination module according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the feedback adjustment module in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0023] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0024] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0025] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0026] Please see Figure 1 As shown, this is a structural schematic diagram of a system for real-time parameter monitoring and data analysis during the forging process according to an embodiment of the present invention. The present invention provides a system for real-time parameter monitoring and data analysis during the forging process, comprising: The acoustic judgment module is used to collect the punching sound signal when the upper die forming surface presses the blank during each stroke, and to determine the sound signal category to which the punching sound signal belongs, and output the sound signal judgment result. The mechanical parameter judgment module is connected to the acoustic judgment module. When the first acoustic signal category judgment result is obtained, the module collects the action time corresponding to the stroke force signal when the upper die forming surface of each stroke presses the blank, and stores the collected stroke force signal and its action time into the force signal set. The friction state determination module is connected to the acoustic determination module and the mechanical parameter determination module. When the second acoustic signal category determination result is obtained, the inertia height of the billet is calculated, and the inertia height is compared with a preset inertia height threshold to determine the category of friction state based on the inertia height comparison result. The cooling monitoring module is connected to the acoustic judgment module, the mechanical parameter judgment module and the friction state judgment module. It is used to determine whether there is a first abnormal cooling area on the surface of the billet that has not been shaken during the cooling cycle, and to determine whether there is a second abnormal cooling area after the shaking treatment when there is a first abnormal cooling area. The feedback adjustment module is connected to the cooling monitoring module and the acoustic judgment module. When the first abnormal cooling area is detected, the acoustic amplitude threshold corresponding to the stroke acoustic signal is linearly adjusted. When the second abnormal cooling area is detected, the stamping environment temperature is adjusted accordingly.

[0027] In this embodiment, the stroke acoustic signal is acquired in real time by an acoustic sensor deployed near the forming surface of the upper die; the stroke force signal and its duration are recorded by a force sensor and a time synchronization device installed on the slider or the upper die body; the inertial height of the billet is obtained and calculated by a high-speed displacement sensor or an image measurement device; the abnormal cooling area is detected by a thermal imager or an infrared temperature sensor to measure the surface temperature distribution of the billet; and the feedback adjustment of the acoustic amplitude threshold and the stamping ambient temperature is achieved by a signal processor connected to the control system and an ambient temperature sensor.

[0028] By accurately acquiring the inertial motion distance of the slider during the stroke and combining it with the graphite emulsion coating coverage and billet mass, the frictional motion distance is calculated, enabling a quantitative determination of the billet displacement caused by friction. A fixed-time-period stroke monitoring window determines the slider's upward speed and inertial displacement, distinguishing the frictional motion distance from the inertial motion. The frictional motion distance can be used to classify the initial processing results of the billet, guiding the adjustment of the coating amount and optimization of cooling strategies. This method accurately reflects the friction state, reducing billet movement deviations caused by excessive friction and improving forming accuracy. By separating inertial motion and frictional motion, quantitative analysis of frictional characteristics during the stroke is achieved, optimizing friction control measures, improving graphite emulsion coating efficiency, reducing surface defect incidence, and providing reliable data for subsequent cooling monitoring and feedback adjustments. The correlation between the frictional motion distance, coating amount, and slider speed ensures process controllability, improves billet surface uniformity and processing consistency, enhances the stability and repeatability of the forging process, and enables real-time evaluation and optimization of the friction-driven process.

[0029] Specifically, the acoustic judgment module includes a time stamping unit, a symmetrical point sampling unit, and an acoustic signal acquisition unit; The time stamp unit is used to obtain the timestamp when the upper die forming surface contacts the blank in each stroke and record it as the first stamp time, and to obtain the timestamp when the slider moves to the bottom dead center and record it as the second stamp time; A symmetrical point-taking unit is used to obtain the time interval between the first marked time and the second marked time, and with the second marked time as the time starting point for symmetrical processing, to obtain the timestamp after the time interval from the time starting point and record it as the third marked time. The acoustic signal acquisition unit is connected to the time marking unit and the symmetrical sampling unit, and uses the time interval from the first marked time to the third marked time as the monitoring window for each stroke, and acquires the acoustic signal within the monitoring window.

[0030] In this embodiment, the upper die forming surface is the surface of the workpiece being formed, installed at the lower end of the slider, used to directly contact the billet and apply forming pressure during the forging stroke; the billet is the metal blank to be processed, placed between the upper die forming surface and the lower die during the stroke and undergoing plastic deformation; the bottom dead center is the lowest position reached by the slider during the stroke, serving as a reference for the end of the stroke; the timestamp is a system time stamp acquired at the moment of a critical action or event, used to record key time nodes during the stroke, wherein the first time stamp is the timestamp when the upper die forming surface first contacts the billet, the second time stamp is the timestamp when the slider moves to the bottom dead center, and the time interval between the two is used to define the monitoring interval; the symmetry processing is based on the second time stamp, extending equidistantly on both sides of the time axis to obtain the third time stamp, which is the timestamp formed after extending the second time stamp by one time interval; a monitoring window is formed between the first time stamp and the third time stamp, which is used to limit the acquisition range of the acoustic signal; the acoustic signal is the acoustic vibration signal generated when the die contacts the billet and undergoes plastic deformation during the stroke.

[0031] It can accurately capture the acoustic vibrations generated by the contact between the die and the blank and the plastic deformation during the stroke, providing reliable data for mechanical parameter judgment, inertial motion analysis and coating amount optimization, and ensuring the controllability of the forming process.

[0032] See Figure 2 As shown, it is a structural schematic diagram of the acoustic judgment module in an embodiment of the present invention; Specifically, the acoustic judgment module also includes an acoustic signal judgment unit; The sound signal judgment unit is used to acquire the sound signal, including sound amplitude and high frequency component, within the monitoring window, and to obtain the first sound signal result when the sound amplitude is greater than or equal to a preset sound amplitude threshold and the high frequency component is greater than or equal to a preset high frequency proportion threshold.

[0033] In this embodiment, the monitoring window is a time interval formed between the first marked time and the third marked time; the acoustic signal includes acoustic amplitude and high-frequency components, the acoustic amplitude is the magnitude of the acoustic signal within the monitoring window, and the high-frequency components are the frequency components in the acoustic signal that exceed a preset reference frequency; the acoustic amplitude threshold is a preset acoustic amplitude critical value, and the high-frequency proportion threshold is a preset high-frequency component proportion critical value; when the acoustic amplitude is greater than or equal to the acoustic amplitude threshold and the high-frequency component is greater than or equal to the high-frequency proportion threshold, a first acoustic signal result is obtained, and the first acoustic signal result is the output result after judging the acoustic signal; The acoustic amplitude threshold and the high-frequency proportion threshold can be set by statistical analysis and experimental calibration based on historical acoustic data of typical strokes during forging. Generally, the acoustic amplitude threshold ranges from 70dB to 120dB, with 85dB to 95dB being the optimal range. In this embodiment, 90dB is used. The high-frequency proportion threshold ranges from 20% to 50%, with 30% to 35% being the optimal range. In this embodiment, 32% is used.

[0034] This enables quantitative analysis of the mechanical state during the stamping process, providing accurate quantitative data for subsequent friction determination, coating amount adjustment, and forming parameter optimization, ensuring force balance during blank stamping and stability during demolding.

[0035] Specifically, the mechanical parameter determination module includes a force acquisition unit and a reaction force detection unit; The force acquisition unit is used to acquire the stroke force signal of the slider in the monitoring window when the first sound signal result is obtained; The reaction force detection unit is connected to the force acquisition unit to obtain the reaction force of the stamping blank on the upper die forming surface after the second mark time, and the fourth mark time is when the reaction force in each stroke is returned to zero.

[0036] In this embodiment, the stroke force signal is the force data of the slider acting on the blank during the stroke; the reaction force detection unit records the reaction force of the upper die forming surface pressing the blank after the second mark time. The reaction force is the feedback force transmitted from the blank to the upper die forming surface when it is subjected to stamping. When the reaction force drops to zero during each stroke, it is determined to be the fourth mark time. The fourth mark time is the moment when the blank is completely separated from the upper die forming surface.

[0037] By continuously monitoring the stroke force signal and reaction force, the dynamic changes of the slider force and the blank force are quantified, and the stress state and release time of the blank during the stroke are accurately determined, thereby providing quantitative data for friction assessment, coating amount optimization and subsequent processing parameter adjustment.

[0038] Specifically, the reaction force detection unit includes an image acquisition subunit and a billet separation time detection subunit; The image acquisition subunit is used to acquire several connected images, including the upper die forming surface and the blank forming protrusion, at a fixed acquisition frequency when the slider moves from the bottom dead center to the top dead center in each stroke. The blank removal time detection subunit is connected to the image acquisition subunit and is used to mark the fourth time based on the several connected images when the coordinates of the upper mold forming surface and the blank forming protrusion in the vertical direction are inconsistent and the reaction force is zero.

[0039] During the movement of the slider from the bottom dead center to the top dead center, the image acquisition subunit acquires connected images at a fixed acquisition frequency. The connected images cover the relative positional changes of the upper mold forming surface and the blank forming protrusions. The acquisition frequency is set to 200fps to ensure that a continuous and clear image sequence can still be obtained during the high-speed forming process. The billet separation time monitoring subunit receives the above-mentioned connection image and extracts the coordinate information of the upper mold forming surface and the billet forming protrusion in the vertical direction; by performing pixel-level comparison of adjacent frame images, it determines whether there is a coordinate offset between the upper mold forming surface and the billet forming protrusion in the vertical direction; when it is detected that the two no longer coincide, and at the same time, it determines that the reaction force drops to zero by combining the reaction force data collected by the pressure sensor, and defines this moment as the fourth mark time. In actual implementation, the slider stroke range is 200mm, and the reaction force sensor sensitivity is 0.5N.

[0040] See Figure 3 As shown, it is a structural schematic diagram of the friction state determination module in an embodiment of the present invention; Specifically, the friction state determination module includes a spray volume detection unit and a distance calculation unit; The spray volume detection unit is used to acquire several spray images of the blank surface and the upper die forming surface at a fixed acquisition frequency when spraying graphite emulsion in each stroke, and to determine the coverage of graphite emulsion spraying based on the several spray images. The distance calculation unit is connected to the spray volume detection unit and is used to determine the frictional motion distance in the inertial motion distance under the graphite emulsion spray coverage.

[0041] In this embodiment, when the spray volume detection unit sprays graphite emulsion in each stroke, it first obtains the initial spray mass. The initial spray mass is directly measured by the nozzle liquid metering device at the beginning of spraying, and the initial spray area is calculated by converting the nozzle diameter and spray pressure parameters. During the spraying process, the spray volume detection unit acquires spray images covering the surface of the blank and the upper mold forming surface at a fixed acquisition frequency. The image acquisition camera is used with a ring light source for auxiliary illumination to ensure clear image grayscale and edges. In the acquired spray images, the boundaries of the sprayed adhesion area are extracted by grayscale threshold segmentation and edge detection, and the sprayed adhesion area is calculated. The coating adhesion quality is obtained by multiplying the coating adhesion area by the liquid film thickness per unit area, where the liquid film thickness per unit area is determined in advance through calibration experiments. The coating coverage is obtained by dividing the coating adhesion mass by the initial coating mass, and is used to characterize the actual adhesion of graphite emulsion on the surface of the blank and the forming surface of the upper mold. After obtaining the coating coverage, the distance calculation unit acquires the inertial motion distance of the corresponding stroke. This inertial motion distance is the displacement of the billet as the slider moves from the bottom dead center to the top dead center. At the same time, the slider's upward speed is calculated based on the time taken for the slider to move from the bottom dead center to the top dead center and the distance between the top and bottom dead centers. The frictional motion distance is obtained by subtracting the displacement caused by the slider's direct upward movement from the inertial motion distance. This frictional motion distance represents the displacement of the billet caused by friction under inertial action. For example, when the spray volume detection unit sprays graphite emulsion in each stroke, it first obtains the initial spray mass. The nozzle liquid metering device measures the initial spray mass as 5g at the start of spraying, and converts this to an initial spray area of ​​2000mm² based on a nozzle diameter of 2mm and a spray pressure of 0.3MPa. During the spraying process, the spray volume detection unit acquires spray images covering the surface of the blank and the upper mold forming surface at a fixed acquisition frequency of 50 Hz. The image acquisition camera has a resolution of 1920×1080 pixels, and a ring light source is used for auxiliary illumination to ensure image grayscale and edge clarity. In the acquired spray images, the boundaries of the sprayed adhesion area are extracted through grayscale thresholding and edge detection, and the sprayed adhesion area is calculated to be 1800mm². mm²; the coating adhesion quality is obtained by multiplying the coating adhesion area by the liquid film thickness per unit area. The liquid film thickness per unit area is determined to be 0.0025 g / mm² through calibration experiments, so the coating adhesion quality is 4.5 g; the coating coverage is obtained by dividing the coating adhesion quality by the initial coating quality, which is 0.9, used to characterize the actual adhesion degree of graphite emulsion on the surface of the blank and the forming surface of the upper mold. After obtaining the coating coverage, the distance calculation unit acquires the inertial motion distance of the corresponding stroke; the distance between the bottom dead center and the top dead center of the slider is 100mm, taking 0.2s, and the slider's upward speed is 500mm / s; the actual measured displacement of the blank as the slider rises is 105mm, and the inertial motion distance is 105mm; the frictional motion distance is obtained by subtracting the displacement caused by the slider's direct rise from the inertial motion distance, which is 5mm. This frictional motion distance represents the displacement of the blank due to friction under inertial action.

[0042] The spray volume detection unit and distance calculation unit accurately determine the friction state of the blank, precisely reflecting the actual adhesion of graphite emulsion on the blank surface and the upper die forming surface. The distance calculation unit measures the inertial motion distance of the blank as it rises with the slider and subtracts the displacement caused by the direct rise of the slider to obtain the frictional motion distance, thereby quantifying the influence of friction on the blank displacement and enabling real-time monitoring and control of the stroke processing. Quantitative determination of spray quality and friction state helps reduce the interference of abnormal friction on the stroke motion, improves the uniformity of blank forming and processing accuracy, and ensures stable contact and processing consistency between the blank surface and the upper die forming surface during production.

[0043] Specifically, the friction state determination module also includes a distance comparison unit; The distance comparison unit is connected to the spray volume detection unit and the distance calculation unit, and is used to compare the inertial motion distance with the preset inertial motion distance threshold to obtain the inertial motion distance comparison result and obtain the category to which the corresponding billet preliminary processing result belongs.

[0044] In this embodiment, the distance comparison unit compares the frictional motion distance with a preset inertial motion distance threshold; if the frictional motion distance is greater than or equal to the preset inertial motion distance threshold, the excessive frictional motion category is obtained, corresponding to the initial processing result of the first blank. If the frictional motion distance is less than the preset inertial motion distance threshold, then the insufficient frictional motion category is obtained, corresponding to the initial processing result of the first blank.

[0045] By comparing several parameters, the friction state can be accurately identified, and the initial processing results of the billet can be classified, thus providing a reliable reference and adjustment basis for the subsequent forming process.

[0046] Specifically, the cooling monitoring module includes a surface detection unit, an interference elimination unit, and a surface re-detection unit; The surface detection unit is used to determine, when the initial processing result of the first billet is obtained, whether the surface of the billet that has not been shaken during the cooling cycle is a first abnormal cooling area where there is no abnormal cooling area and the cooling rate is greater than a preset cooling threshold. An interference elimination unit, connected to the surface detection unit, is used to shake the billet when there is an abnormal cooling area. The surface re-detection unit, connected to the interference elimination unit, is used to determine whether there is a second abnormal cooling area on the surface of the billet after the shaking process, where the cooling rate is greater than a preset cooling threshold.

[0047] In this embodiment, after obtaining the initial processing result of the first blank, the surface detection unit judges the surface of the blank that has not been shaken during the cooling cycle; If there is a region on the surface of the billet where the cooling rate is greater than the preset cooling threshold, it is determined that there is a first abnormal cooling region. If there is no area on the surface of the billet where the cooling rate is greater than the preset cooling threshold, it is determined that there is no first abnormal cooling area.

[0048] When the first abnormal cooling area exists, the interference elimination unit shakes the billet. After the shaking process, the surface re-inspection unit re-evaluates the surface of the billet; If there are still areas on the surface of the billet where the cooling rate is greater than the preset cooling threshold, it is determined that there is a second abnormal cooling area. If there is no area on the surface of the billet where the cooling rate is greater than the preset cooling threshold, it is determined that there is no second abnormal cooling area. For example, in this embodiment, the preset cooling threshold is the critical value of the rate of temperature drop on the surface of the billet during the cooling cycle. It can be obtained by conducting temperature monitoring experiments on multiple test billets under standard production conditions, and the maximum safe cooling rate under normal cooling conditions is selected as the threshold. The preset cooling threshold is set to a temperature drop of 15°C per second, which is used to determine whether there is an abnormal cooling rate on the surface of the billet during the cooling cycle. The inertial motion distance threshold is set to 5 mm to compare the frictional motion distance with the standard range, thereby obtaining the category of the initial processing result of the billet; The vibration treatment is a mechanical vibration action applied to the billet when there are abnormal cooling areas on the billet surface, in order to improve the heat conduction and uniformity of the billet surface. In actual production, the vibration treatment can be carried out by slightly vibrating the slider up and down or by applying mechanical vibration with a fixed frequency and amplitude using a vibration table. The vibration frequency and amplitude are determined by experiments, so that the rate of temperature drop of the billet surface is reduced to below the preset cooling threshold.

[0049] By setting the preset cooling threshold and inertial motion distance threshold appropriately, the category of the initial processing result of the billet can be accurately determined, thereby ensuring the uniformity of the cooling process and improving the forming quality and production stability.

[0050] See Figure 4 As shown, it is a structural schematic diagram of the feedback adjustment module in an embodiment of the present invention; Specifically, the feedback adjustment module includes a first feedback unit and a second feedback unit; The first feedback unit is used to adjust the threshold corresponding to the stroke acoustic signal when the abnormal cooling area is the first abnormal cooling area. The second feedback unit, connected to the first feedback unit, is used to adjust the stamping environment temperature when the abnormal cooling area is the second abnormal cooling area.

[0051] Specifically, the first feedback unit includes a threshold adjustment subunit and a high-frequency adjustment subunit; The threshold adjustment subunit is used to linearly adjust the preset sound amplitude threshold in the acoustic judgment module according to the preset sound amplitude threshold adjustment ratio coefficient when the first abnormal cooling area is obtained. The high-frequency adjustment subunit, connected to the threshold adjustment subunit, is used to adjust the high-frequency proportion threshold by a fixed ratio when an abnormal temperature region still occurs after the preset sound amplitude threshold adjustment number is greater than the standard adjustment number.

[0052] In this embodiment, the cooling monitoring module obtains the surface temperature distribution of the un-vibrated billet during the cooling cycle through the surface detection unit, calculates the actual cooling rate for each detection point, and compares it with the preset cooling threshold. For example, if the cooling rate of a certain area is greater than the preset cooling threshold of 100°C / s, then the area is determined to be the first abnormal cooling area, and the first billet initial processing result is output. The interference elimination unit shakes the first abnormal cooling area detected to redistribute the surface of the billet for uniform cooling. Then, the surface re-detection unit measures the surface temperature distribution of the billet and calculates the cooling rate. If, after shaking, there is still an area whose cooling rate is greater than the preset cooling threshold, then the area is determined to be the second abnormal cooling area. When the feedback adjustment module detects the first abnormal cooling area, it activates the first feedback unit and adjusts the preset sound amplitude threshold in the acoustic judgment module by a linear adjustment coefficient of 10% through the threshold adjustment subunit. It then reacquires the stroke sound signal for judgment. In this embodiment, the number of adjustments is 3. If the first abnormal cooling area still exists after three adjustments, the high-frequency adjustment subunit is activated, and the high-frequency proportion threshold in the acoustic judgment module is adjusted by a fixed ratio of 5%, and the abnormal area is re-judged. If necessary, this step is repeated until the abnormal area is eliminated. When the second abnormal cooling area is detected, the second feedback unit is activated to adjust the stamping environment temperature.

[0053] By combining cooling monitoring with feedback adjustment, precise control of abnormal cooling on the billet surface is achieved; through surface detection and vibration processing, the first and second abnormal cooling areas are effectively identified and eliminated; dynamic adjustment of acoustic threshold and high-frequency proportion threshold makes the judgment of stroke acoustic signals more accurate and avoids monitoring errors caused by temperature abnormalities.

[0054] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0055] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A system for real-time monitoring and data analysis of parameters during the forging process, characterized in that, include: The acoustic judgment module is used to collect the punching sound signal when the upper die forming surface presses the blank during each stroke, and to determine the sound signal category to which the punching sound signal belongs, and output the sound signal judgment result. The mechanical parameter judgment module is connected to the acoustic judgment module. When the first acoustic signal category judgment result is obtained, the module collects the action time corresponding to the stroke force signal when the upper die forming surface of each stroke presses the blank, and stores the collected stroke force signal and its action time into the force signal set. The friction state determination module is connected to the acoustic determination module and the mechanical parameter determination module. When the second acoustic signal category determination result is obtained, the inertia height of the billet is calculated, and the inertia height is compared with a preset inertia height threshold to determine the category of friction state based on the inertia height comparison result. The cooling monitoring module is connected to the acoustic judgment module, the mechanical parameter judgment module and the friction state judgment module. It is used to determine whether there is a first abnormal cooling area on the surface of the billet that has not been shaken during the cooling cycle, and to determine whether there is a second abnormal cooling area after the shaking treatment when there is a first abnormal cooling area. The feedback adjustment module is connected to the cooling monitoring module and the acoustic judgment module. When the first abnormal cooling area is detected, the acoustic amplitude threshold corresponding to the stroke acoustic signal is linearly adjusted. When the second abnormal cooling area is detected, the stamping environment temperature is adjusted accordingly.

2. The system for real-time monitoring and data analysis of parameters during forging as described in claim 1, characterized in that, The acoustic judgment module includes a time stamping unit, a symmetrical point sampling unit, and an acoustic signal acquisition unit; The time stamp unit is used to obtain the timestamp when the upper die forming surface contacts the blank in each stroke and record it as the first stamp time, and to obtain the timestamp when the slider moves to the bottom dead center and record it as the second stamp time; A symmetrical point-taking unit is used to obtain the time interval between the first marked time and the second marked time, and with the second marked time as the time starting point for symmetrical processing, to obtain the timestamp after the time interval from the time starting point and record it as the third marked time. The acoustic signal acquisition unit is connected to the time marking unit and the symmetrical sampling unit, and uses the time interval from the first marked time to the third marked time as the monitoring window for each stroke, and acquires the acoustic signal within the monitoring window.

3. The system for real-time monitoring and data analysis of parameters during forging as described in claim 2, characterized in that, The acoustic judgment module also includes an acoustic signal judgment unit; The sound signal judgment unit is used to acquire the sound signal, including sound amplitude and high frequency component, within the monitoring window, and to obtain the first sound signal result when the sound amplitude is greater than or equal to a preset sound amplitude threshold and the high frequency component is greater than or equal to a preset high frequency proportion threshold.

4. The system for real-time monitoring and data analysis of parameters during the forging process according to claim 3, characterized in that, The mechanical parameter determination module includes an action force acquisition unit and a reaction force detection unit; The force acquisition unit is used to acquire the stroke force signal of the slider in the monitoring window when the first sound signal result is obtained; The reaction force detection unit is connected to the force acquisition unit to obtain the reaction force of the stamping blank on the upper die forming surface after the second mark time, and the fourth mark time is when the reaction force in each stroke is returned to zero.

5. The system for real-time monitoring and data analysis of parameters during the forging process according to claim 4, characterized in that, The reaction force detection unit includes an image acquisition subunit and a billet separation time monitoring subunit; The image acquisition subunit is used to acquire several connected images, including the upper die forming surface and the blank forming protrusion, at a fixed acquisition frequency when the slider moves from the bottom dead center to the top dead center in each stroke. The blank removal time detection subunit is connected to the image acquisition subunit and is used to mark the fourth time based on the several connected images when the coordinates of the upper mold forming surface and the blank forming protrusion in the vertical direction are inconsistent and the reaction force is zero.

6. The system for real-time monitoring and data analysis of parameters during forging as described in claim 5, characterized in that, The friction state determination module includes a spray volume detection unit and a distance calculation unit; The spray volume detection unit is used to acquire several spray images of the blank surface and the upper die forming surface at a fixed acquisition frequency when spraying graphite emulsion in each stroke, and to determine the coverage of graphite emulsion spraying based on the several spray images. The distance calculation unit is connected to the spray volume detection unit and is used to determine the frictional motion distance in the inertial motion distance under the graphite emulsion spray coverage.

7. The system for real-time monitoring and data analysis of parameters during forging as described in claim 6, characterized in that, The friction state determination module also includes a distance comparison unit; The distance comparison unit is connected to the spray volume detection unit and the distance calculation unit, and is used to compare the inertial motion distance with the preset inertial motion distance threshold to obtain the inertial motion distance comparison result and obtain the category to which the corresponding billet preliminary processing result belongs.

8. The system for real-time monitoring and data analysis of parameters during forging as described in claim 7, characterized in that, The cooling monitoring module includes a surface detection unit, an interference elimination unit, and a surface re-detection unit; The surface detection unit is used to determine, when the initial processing result of the first billet is obtained, whether the surface of the billet that has not been shaken during the cooling cycle is a first abnormal cooling area with a cooling rate greater than a preset cooling threshold. An interference elimination unit, connected to the surface detection unit, is used to shake the billet when there is an abnormal cooling area. The surface re-detection unit, connected to the interference elimination unit, is used to determine whether there is a second abnormal cooling area on the surface of the billet after the shaking process, where the cooling rate is greater than a preset cooling threshold.

9. The system for real-time monitoring and data analysis of parameters during forging as described in claim 8, characterized in that, The feedback adjustment module includes a first feedback unit and a second feedback unit; The first feedback unit is used to adjust the threshold corresponding to the stroke acoustic signal when the abnormal cooling area is the first abnormal cooling area. The second feedback unit, connected to the first feedback unit, is used to adjust the stamping environment temperature when the abnormal cooling area is the second abnormal cooling area.

10. The system for real-time monitoring and data analysis of parameters during forging according to claim 9, characterized in that, The first feedback unit includes a threshold adjustment subunit and a high-frequency adjustment subunit; The threshold adjustment subunit is used to linearly adjust the preset sound amplitude threshold in the acoustic judgment module according to the preset sound amplitude threshold adjustment ratio coefficient when the first abnormal cooling area is obtained. The high-frequency adjustment subunit, connected to the threshold adjustment subunit, is used to adjust the high-frequency proportion threshold by a fixed ratio when an abnormal temperature region still occurs after the preset sound amplitude threshold adjustment number is greater than the standard adjustment number.

Images