An adaptive dispensing machine control system based on sensor feedback
Through the sensor feedback adaptive control system, the parameters of the dispenser are identified and adjusted in real time, and the efficiency and uniformity problems of traditional dispensers under workpieces or sealed areas are solved, achieving automated and efficient dispensing control.
Patent Information
- Application Number
- CN202410485306.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-22
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-04-22
AI Technical Summary
When facing workpieces or sealed areas of different sizes, traditional dispensers need to manually adjust parameters, which increases the complexity and processing time of the dispensing process, and cannot identify size changes and adjust the amount of glue in real time, resulting in uniform dispensing. Poor degree.
Adaptive dispenser control system based on sensor feedback is adopted to obtain the sealing area image through the data acquisition module, judge the changing sealing area, calculate the glue adjustment amount, predict the future arrival time, adjust the moving speed, and realize automatic control.
Adaptive control of workpieces or sealing areas of different sizes is achieved, ensuring uniformity of dispensing, improving production efficiency and glue production accuracy.
Smart Images

Figure CN118305048B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of glue dispensing machine control, and more specifically, to an adaptive glue dispensing machine control system based on sensor feedback. Background Art
[0002] A glue dispensing machine is a device used to apply adhesive or coating to a workpiece during the manufacturing process. It is also called a glue coater, glue dripper, glue dispenser or glue filling machine. It is specifically used to accurately control liquid fluids and drip and apply them to the surface or interior of a product. It is widely used in industries such as automobile manufacturing, electronic products (3C), building materials, food processing and packaging. However, traditional glue dispensing systems require fixed control parameters (such as pressure, etc.) to be set in advance during the glue dispensing process. When faced with workpieces or sealing areas of different sizes, manual intervention is usually required to adjust the parameters of the glue dispensing system, which increases the complexity and processing time of the glue dispensing process. Therefore, it is necessary to propose a new adaptive glue dispensing machine control system based on sensor feedback to adapt to workpieces or sealing areas of different sizes, thereby improving production efficiency.
[0003] At present, there is a lack of adaptive dispensing machine control systems that can adapt to workpieces of different sizes or sealing areas. Of course, there are also some documents on partially automated dispensing control technology. For example, the Chinese patent with authorization announcement number CN101712022B discloses a method for controlling a dispensing machine to perform dispensing. Although the above method can make the amount of glue controlled by the dispensing machine more accurate, research and practical application of the above method and the prior art have found that the above method and the prior art have at least the following defects:
[0004] (1) There is a lack of detection and judgment of sealing areas of different sizes. It is impossible to identify the sealing area with size changes, and it is impossible to calculate the required adjustment amount of the dispensing amount in real time according to the sealing area with size changes. Furthermore, it is impossible to determine the dispensing adjustment air pressure of the dispensing machine;
[0005] (2) It is impossible to predict the future time when the dispensing machine will arrive at the sealing area with changed size, and it is impossible to correct the movement speed of the dispensing machine based on the adjusted glue output, so it is impossible to adapt to workpieces or sealing areas of different sizes. Furthermore, it is impossible to ensure the uniformity of dispensing when dispensing workpieces or sealing areas of different sizes. Summary of the invention
[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an adaptive dispensing machine control system based on sensor feedback.
[0007] To achieve the above object, the present invention provides the following technical solutions:
[0008] An adaptive dispensing machine control system based on sensor feedback, the system comprising:
[0009] A data acquisition module is used to divide the sealing area of the glue-dispensing workpiece into M sealing sections, and when the glue-dispensing machine is controlled to reach the i-th sealing section according to a preset motion path, an area image of the i+r-th sealing section is obtained;
[0010] An image judgment module, used for judging whether the i+rth sealing section is a variable sealing area according to the regional image, where M, i and r are integers greater than zero;
[0011] The air pressure determination module is used to obtain the current glue output of the glue dispenser and the sealing size of the changed sealing area when a changed sealing area appears, and calculate the glue output adjustment amount of the glue dispenser based on the current glue output amount and the sealing size, and determine the glue dispensing adjustment air pressure of the glue dispenser according to the mapping relationship between the glue output adjustment amount and the glue dispensing air pressure;
[0012] A time prediction module is used to obtain time prediction feature data, input the time prediction feature data into a preset time prediction model, and predict the future time point when the dispensing machine will arrive at the changing sealing area;
[0013] The speed correction module is used to retrieve the current moving speed of the dispensing machine, combine the current moving speed, the glue output adjustment amount, the sealing size of the changed sealing area and the glue dispensing adjustment air pressure into the speed correction feature data, and input them into the preset speed change correction model to obtain the moving adjustment speed of the dispensing machine;
[0014] The adaptive control module is used to automatically adjust the dispensing machine based on the dispensing adjustment air pressure and the movement adjustment speed when it is at a future time point.
[0015] Further, the determining whether the (i+r)th sealing section is a variable sealing area includes:
[0016] Extracting the regional image of the i+rth sealed section, and calling the regional image of the ikth sealed section, where k is an integer greater than zero;
[0017] Mark the regional image of the i+rth sealed section as a comparison image, and use the regional image of the ikth sealed section as a reference image;
[0018] The pixel areas of the sealed sections in the comparison image and the reference image are respectively obtained by an image processing algorithm;
[0019] using the pixel area of the sealed section in the comparison image as the comparison pixel area, and using the pixel area of the sealed section in the reference image as the reference pixel area;
[0020] The comparison pixel area and the reference pixel area are numerically compared. If the values of the comparison pixel area and the reference pixel area are equal, the i+rth sealing segment is determined to be a non-changing sealing area; if the values of the comparison pixel area and the reference pixel area are not equal, the i+rth sealing segment is determined to be a changing sealing area.
[0021] Further, after determining whether the (i+r)th sealing section is a variable sealing area, the method further includes:
[0022] If it is determined that the i+rth sealing section is a non-changing sealing area, r=r+1 is set and the data acquisition module is returned.
[0023] Furthermore, the sealing dimension includes an actual length of the sealing area, an actual width of the sealing area, and an actual depth of the sealing area.
[0024] Further, the calculation of the glue output adjustment amount of the glue dispensing machine includes:
[0025] Extract the sealing size of the i-th sealing section, the current glue output of the glue dispenser, and the sealing size of the changing sealing area;
[0026] The sealing size of the i-th sealing section, the current glue output and the sealing size are input into a pre-built mathematical model to calculate the glue output adjustment amount of the glue dispenser; wherein the pre-built mathematical model is: Where: Δδ is the glue discharge adjustment amount, δ1 is the current glue discharge amount, S1 is the volume of the i-th sealing section, S2 is the volume of the changing sealing area, k is the volume ratio correction weight greater than zero, and R is the comprehensive weight factor.
[0027] Furthermore, the time prediction characteristic data includes the current moving speed of the glue dispenser, the coordinate position of the changing sealing area, the coordinate position of the i-th sealing section, and the time point when the glue dispenser is in the i-th sealing section.
[0028] Furthermore, the generation logic of the preset time prediction model is as follows:
[0029] Obtaining historical dispensing machine time training data, and dividing the historical dispensing machine time training data into a time prediction training set and a time prediction test set; the historical dispensing machine time training data includes time prediction feature data and its corresponding future time point;
[0030] Constructing a first regression network, taking the time prediction feature data in the time prediction training set as the first regression network input data, taking the corresponding future time point in the time prediction training set as the first regression network output data, training the first regression network, and obtaining an initial time prediction network;
[0031] The time prediction test set is used to perform a model test on the initial time prediction network, and the corresponding initial time prediction network with a value less than or equal to a preset first test error threshold is input as the preset time prediction model.
[0032] Furthermore, the generation logic of the preset speed change correction model is as follows:
[0033] Obtain historical speed correction training data, and divide the historical dispensing machine time training data into a speed correction training set and a speed correction test set; the historical speed correction training data includes speed correction feature data and its corresponding movement adjustment speed;
[0034] Constructing a second regression network, taking the speed correction feature data in the speed correction training set as the second regression network input data, taking the corresponding movement adjustment speed in the speed correction training set as the second regression network output data, training the second regression network, and obtaining an initial speed change correction network;
[0035] The initial speed change correction network is model tested using the speed correction test set, and the corresponding initial speed change correction network that is less than or equal to the preset second test error threshold is input as the preset speed change correction model.
[0036] Furthermore, the determination logic of the movement adjustment speed in the historical movement speed correction training data is as follows:
[0037] a1: When the changed sealing area is determined and the dispensing machine is used to dispense glue to the changed sealing area according to the air pressure adjusted by the dispensing, the current moving speed v of the dispensing machine is obtained;
[0038] a2: Adjust the value of the current moving speed v to obtain the adjusted moving speed Q, where both v and Q are integers greater than zero;
[0039] a3: subdivide the variable sealing area into G sealing subsections, and measure the actual glue coating thickness of each sealing subsection after dispensing according to the adjustment of the moving speed G and the dispensing adjustment air pressure, where G is an integer greater than zero;
[0040] a4: extract the standard glue coating thickness, calculate the uniformity coefficient according to the actual glue coating thickness and the standard glue coating thickness, compare the uniformity coefficient with the uniformity coefficient threshold, if the uniformity coefficient is less than the uniformity coefficient threshold, return to step a2; if the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, adjust the moving speed G as the moving adjustment speed;
[0041] a5: Repeat the above steps a2 to a4 until the moving adjustment speed is obtained, and then end the loop.
[0042] Furthermore, the calculation formula of the uniformity coefficient is: Where: UD is the uniformity coefficient, h i is the actual glue coating thickness of the g-th sealing sub-section, and h is the standard glue coating thickness method.
[0043] Compared with the prior art, the present invention has the following beneficial effects:
[0044] The present application discloses an adaptive glue dispenser control system based on sensor feedback, including: when the glue dispenser is controlled to arrive at the i-th sealing section according to a preset motion path, a regional image of the i+r-th sealing section is obtained; whether the i+r-th sealing section is a variable sealing area is determined; when a variable sealing area appears, the current glue output amount and sealing size are obtained, and the glue output adjustment amount is calculated based on the current glue output amount and sealing size, and the glue dispensing adjustment air pressure is determined according to the glue output adjustment amount; time prediction feature data is obtained, and the future time point when the glue dispenser arrives at the variable sealing area is predicted based on the time prediction feature data; the speed correction feature data of the glue dispenser is estimated according to the speed correction feature data. Moving adjustment speed; when at a future time point, the dispensing machine is automatically controlled based on the dispensing adjustment air pressure and the moving adjustment speed; based on the above process, the present invention can identify the sealing area where the size changes, and can calculate the adjustment amount of the required dispensing amount in real time according to the sealing area with the size change, and further, can determine the dispensing adjustment air pressure of the dispensing machine; in addition, the present invention predicts the future time when the dispensing machine arrives at the sealing area with the size change, and corrects the moving speed of the dispensing machine, which is beneficial for the dispensing machine to adapt to workpieces or sealing areas of different sizes, and further, it is beneficial to ensure the uniformity of dispensing when dispensing workpieces or sealing areas of different sizes. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 A schematic diagram of the module structure of a self-adaptive dispensing machine control system based on sensor feedback provided by the present invention;
[0046] Figure 2 A flow chart of a method for controlling an adaptive dispensing machine based on sensor feedback provided by the present invention. DETAILED DESCRIPTION
[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0048] Example 1
[0049] See also Figure 1 As shown, this embodiment discloses an adaptive dispensing machine control system based on sensor feedback, and the system includes:
[0050] The data acquisition module 110 is used to divide the sealing area of the glue-dispensing workpiece into M sealing sections, and when the glue-dispensing machine is controlled to reach the i-th sealing section according to the preset motion path, the regional image of the i+r-th sealing section is obtained;
[0051] It should be noted that: the sealing area of the workpiece to be glued is divided into M sealing sections, which is determined by technicians in advance according to the shape of the workpiece to be glued; it can be understood that the section lengths of the M sealing sections are equal; it should also be noted that the preset motion path is generated by the path generation program of the existing glue dispensing machine or is set in advance by a technician, which is not the focus of the present invention and can be based on the existing technology. Therefore, no further elaboration is made on this;
[0052] It should be understood that: the dispensing machine is equipped with at least two camera sensors, one of which is vertically installed and used to collect images of the current sealing section where the dispensing machine is located, that is, the regional image of the i-th sealing section; the other camera sensor is installed at an angle of 30 degrees or 40 degrees, and is used to collect images of the non-dispensing area, that is, the regional image of the i+r-th sealing section.
[0053] An image determination module 120, for determining whether the i+rth sealing section is a variable sealing area according to the regional image, where M, i and r are integers greater than zero;
[0054] In implementation, the step of determining whether the (i+r)th sealing section is a variable sealing area includes:
[0055] Extracting the regional image of the i+rth sealed section, and calling the regional image of the ikth sealed section, where k is an integer greater than zero;
[0056] Mark the regional image of the i+rth sealed section as a comparison image, and use the regional image of the ikth sealed section as a reference image;
[0057] The pixel areas of the sealed sections in the comparison image and the reference image are respectively obtained by an image processing algorithm;
[0058] It should be noted that: when the pixel areas of the sealed sections in the comparison image and the reference image are respectively obtained by using an image processing algorithm; wherein the image processing algorithm is a specific one of a K-means clustering algorithm, an edge detection algorithm, a threshold segmentation algorithm, a detection algorithm based on pixel color / intensity, etc., and the edge detection algorithm includes but is not limited to one of a Sobel or Canny detection algorithm, etc.;
[0059] using the pixel area of the sealed section in the comparison image as the comparison pixel area, and using the pixel area of the sealed section in the reference image as the reference pixel area;
[0060] The comparison pixel area and the reference pixel area are numerically compared. If the comparison pixel area and the reference pixel area have the same numerical value, the i+rth sealing section is determined to be a non-changing sealing area; if the comparison pixel area and the reference pixel area have different numerical values, the i+rth sealing section is determined to be a changing sealing area.
[0061] In implementation, after determining whether the i+rth sealing section is a variable sealing area, the following steps are performed:
[0062] If it is determined that the i+rth sealing section is a non-changing sealing area, r=r+1 is set and the data collection module 110 is returned.
[0063] The air pressure determination module 130 is used to obtain the current glue output amount of the glue dispenser and the sealing size of the changed sealing area when a changed sealing area appears, and calculate the glue output adjustment amount of the glue dispenser based on the current glue output amount and the sealing size, and determine the glue dispensing adjustment air pressure of the glue dispenser according to the mapping relationship between the glue output adjustment amount and the glue dispensing air pressure;
[0064] Specifically, the sealing dimensions include the actual length of the sealing area, the actual width of the sealing area, and the actual depth of the sealing area;
[0065] It should be noted that: the current glue output of the glue dispensing machine is detected by a preset pressure sensor or a flow meter installed on the glue pipeline; the sealing size of the variable sealing area is obtained based on the regional image analysis of the variable sealing area, or is input in advance by a technician; further explanation is that when the regional image of the variable sealing area is obtained, the pixel length, pixel width and pixel depth of the variable sealing area are obtained by using an existing image processing algorithm, and the pixel length, pixel width and pixel depth are proportionally converted according to a preset proportional relationship to obtain the actual length, the actual width of the sealing area and the actual depth of the sealing area; the preset proportional relationship is determined by the technician in advance by experiments;
[0066] In implementation, the step of calculating the glue adjustment amount of the glue dispensing machine includes:
[0067] Extract the sealing size of the i-th sealing section, the current glue output of the glue dispenser, and the sealing size of the changing sealing area;
[0068] The sealing size of the i-th sealing section, the current glue output and the sealing size are input into a pre-built mathematical model to calculate the glue output adjustment amount of the glue dispenser; wherein the pre-built mathematical model is: Where: Δδ is the glue adjustment amount, δ1 is the current glue amount, S1 is the volume of the i-th sealing section, S2 is the volume of the changing sealing area, k is the volume ratio correction weight greater than zero, and R is the comprehensive weight factor;
[0069] It should be noted that: S1 and S2 are calculated based on the sealing dimensions of the i-th sealing section and the variable sealing area, respectively, and the calculation formula is: S=L×W×H, where: S is the volume of the i-th sealing section or the volume of the variable sealing area, L is the volume of the i-th sealing section or the actual length of the variable sealing area, W is the volume of the i-th sealing section or the actual width of the variable sealing area, and H is the volume of the i-th sealing section or the actual depth of the variable sealing area;
[0070] It should also be noted that the mapping relationship between the glue output adjustment amount and the glue dispensing air pressure is pre-stored in the system database, and there are multiple mapping relationships, each of which contains a specific glue output adjustment amount and the glue dispensing air pressure associated with the glue output adjustment amount; each of the mapping relationships is manually associated in advance by technical personnel, and each glue dispensing air pressure associated with each glue output adjustment amount is determined by specific experimental results.
[0071] The time prediction module 140 is used to obtain time prediction feature data, input the time prediction feature data into a preset time prediction model, and predict the future time point when the dispensing machine arrives at the changed sealing area;
[0072] Specifically, the time prediction feature data includes the current moving speed of the glue dispenser, the coordinate position of the changed sealing area, the coordinate position of the i-th sealing section, and the time point when the glue dispenser is in the i-th sealing section;
[0073] In implementation, the generation logic of the preset time prediction model is as follows:
[0074] Obtaining historical dispensing machine time training data, and dividing the historical dispensing machine time training data into a time prediction training set and a time prediction test set; the historical dispensing machine time training data includes time prediction feature data and its corresponding future time point;
[0075] It should be noted that: the time prediction feature data in the historical dispensing machine time training data is collected by various sensors, including but not limited to laser sensors, timers and speed sensors; the corresponding future time points in the historical dispensing machine time training data are recorded by technicians. A further example is that, during the historical experimental test process, the time when the dispensing machine arrives at the i-th sealing section is recorded as T1, and the time when the dispensing machine arrives at the changing sealing area is T2, then T2 is used as the future time point;
[0076] Constructing a first regression network, taking the time prediction feature data in the time prediction training set as the first regression network input data, taking the corresponding future time point in the time prediction training set as the first regression network output data, training the first regression network, and obtaining an initial time prediction network;
[0077] Using the time prediction test set to perform a model test on the initial time prediction network, inputting a corresponding initial time prediction network that is less than or equal to a preset first test error threshold as a preset time prediction model;
[0078] It should be noted that: the first regression network is a specific one of algorithm models such as decision tree regression, random forest regression, polynomial regression, support vector machine regression or neural network regression.
[0079] The speed correction module 150 is used to retrieve the current speed of the dispensing machine, combine the current speed, the glue output adjustment amount, the sealing size of the changed sealing area and the glue dispensing adjustment air pressure into speed correction feature data, and input them into a preset speed change correction model to obtain the movement adjustment speed of the dispensing machine;
[0080] In implementation, the generation logic of the preset speed change correction model is as follows:
[0081] Obtain historical speed correction training data, and divide the historical dispensing machine time training data into a speed correction training set and a speed correction test set; the historical speed correction training data includes speed correction feature data and its corresponding movement adjustment speed;
[0082] It should be noted that the speed correction feature data in the historical speed correction training data is obtained through various sensors and analysis and processing. The details of the analysis and processing process are described above, and will not be repeated here.
[0083] The logic for determining the movement adjustment speed in the historical movement speed correction training data is as follows:
[0084] a1: When the changed sealing area is determined and the dispensing machine is used to dispense glue to the changed sealing area according to the air pressure adjusted by the dispensing, the current moving speed v of the dispensing machine is obtained;
[0085] a2: Adjust the value of the current moving speed v to obtain the adjusted moving speed Q, where both v and Q are integers greater than zero;
[0086] It should be noted that the adjustment of the value of the current moving speed v includes positive adjustment and negative adjustment. The positive adjustment is to set Q=v+d, and the negative adjustment is to set Q=vd. Further explanation is that the current moving speed v is artificially increased or decreased by d, and then the moving speed Q is obtained, where d is an integer greater than zero.
[0087] a3: subdivide the variable sealing area into G sealing subsections, and measure the actual glue coating thickness of each sealing subsection after dispensing according to the adjustment of the moving speed G and the dispensing adjustment air pressure, where G is an integer greater than zero;
[0088] a4: extract the standard glue coating thickness, calculate the uniformity coefficient according to the actual glue coating thickness and the standard glue coating thickness, compare the uniformity coefficient with the uniformity coefficient threshold, if the uniformity coefficient is less than the uniformity coefficient threshold, return to step a2; if the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, adjust the moving speed G as the moving adjustment speed;
[0089] The calculation formula of the uniformity coefficient is: Where: UD is the uniformity coefficient, h i is the actual glue coating thickness of the g-th sealing subsection, and h is the standard glue coating thickness;
[0090] It should be noted that: after executing the loop, that is, each time returning to step a2, d=d+1 or d=d-1 will be set; it can be understood that if the initial speed adjustment does not meet the conditions, then on the basis of adjusting the moving speed Q, the positive adjustment and negative adjustment of the current moving speed v are repeatedly performed, that is, the size of d is adjusted on the basis of adjusting the moving speed Q until the moving adjustment speed is obtained;
[0091] a5: Repeat the above steps a2 to a4 until the moving adjustment speed is obtained, and then end the loop;
[0092] It should be understood that when adjusting the glue output of the glue dispenser according to the sealing areas of different sizes, it is also necessary to adjust the moving speed of the glue dispenser, otherwise it will cause the fluid to accumulate or discontinuity in the sealing area (that is, some positions in the sealing area are not coated with fluid, or the amount of fluid coated is too small and does not meet the standard);
[0093] It should be noted that: the standard glue coating thickness is pre-stored in the system database, which represents that the fluid in each sealing sub-section of the sealing area needs to reach the set thickness; wherein, the actual glue coating thickness of each sealing sub-section is measured by a thickness sensor;
[0094] Constructing a second regression network, taking the speed correction feature data in the speed correction training set as the second regression network input data, taking the corresponding movement adjustment speed in the speed correction training set as the second regression network output data, training the second regression network, and obtaining an initial speed change correction network;
[0095] The initial speed change correction network is tested using the speed correction test set, and the corresponding initial speed change correction network whose error is less than or equal to the preset second test error threshold is input as the preset speed change correction model;
[0096] It should be noted that: like the above-mentioned first regression network, the second regression network is a specific one of algorithm models such as decision tree regression, random forest regression, polynomial regression, support vector machine regression or neural network regression.
[0097] An adaptive control module 160 is used to automatically adjust the dispensing machine based on the dispensing adjustment air pressure and the movement adjustment speed at a future time point;
[0098] It should be noted that: the above modules are remotely connected via wireless or wired means;
[0099] It can be understood that: when it is at a future time point, it means that the glue dispensing machine has reached the changing sealing area; a further explanation is that the glue dispensing machine reaches a sealing area of another size from a sealing area of one size. At this time, it is necessary to adjust the glue output of the glue dispensing machine according to the glue dispensing adjustment air pressure to make it meet the glue dispensing standard of the sealing area of another size; further, the current moving speed of the glue dispensing machine is adjusted according to the moving adjustment speed to avoid fluid accumulation or fluid discontinuity caused by changes in the glue output.
[0100] Example 2
[0101] See also Figure 2 As shown, based on the same inventive concept, referring to the above embodiment 1, this embodiment discloses a method for controlling an adaptive dispensing machine based on sensor feedback. The contents not detailed in this embodiment are described in the above embodiment 1. The method includes:
[0102] S201: Demarcate the sealing area of the workpiece to be glued into M sealing sections, and when the glue dispenser is controlled to reach the i-th sealing section according to a preset motion path, obtain a regional image of the i+r-th sealing section;
[0103] S202: judging whether the i+rth sealing section is a variable sealing area according to the regional image, where M, i and r are integers greater than zero;
[0104] S203: when a changed sealing area appears, the current glue output amount of the glue dispensing machine and the sealing size of the changed sealing area are obtained, and the glue output adjustment amount of the glue dispensing machine is calculated based on the current glue output amount and the sealing size, and the glue dispensing adjustment air pressure of the glue dispensing machine is determined according to the mapping relationship between the glue output adjustment amount and the glue dispensing air pressure;
[0105] S204: Acquire time prediction feature data, input the time prediction feature data into a preset time prediction model, and predict the future time point when the dispensing machine will arrive at the changed sealing area;
[0106] S205: Retrieve the current moving speed of the glue dispensing machine, combine the current moving speed, the glue discharge adjustment amount, the sealing size of the changed sealing area and the glue dispensing adjustment air pressure into moving speed correction feature data, and input them into a preset moving speed change correction model to obtain the moving adjustment speed of the glue dispensing machine;
[0107] S206: When the time is at a future point, the dispensing machine is automatically regulated based on the dispensing adjustment air pressure and the movement adjustment speed.
[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.
[0109] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DRD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0110] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0112] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0114] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0115] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0116] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. An adaptive dispensing machine control system based on sensor feedback, characterized in that: The system comprises: A data acquisition module is used to divide the sealing area of the glue-dispensing workpiece into M sealing sections, and when the glue-dispensing machine is controlled to reach the i-th sealing section according to a preset motion path, an area image of the i+r-th sealing section is obtained; An image judgment module, used for judging whether the i+rth sealing section is a variable sealing area according to the regional image, where M, i and r are integers greater than zero; The air pressure determination module is used to obtain the current glue output of the glue dispensing machine and the sealing size of the changed sealing area when a changed sealing area appears, and calculate the glue output adjustment amount of the glue dispensing machine based on the current glue output amount and the sealing size of the changed sealing area, and determine the glue dispensing adjustment air pressure of the glue dispensing machine according to the mapping relationship between the glue output adjustment amount and the glue dispensing air pressure; The step of calculating the glue adjustment amount of the glue dispensing machine includes: Extract the sealing size of the i-th sealing section, the current glue output of the glue dispenser, and the sealing size of the changing sealing area; The sealing size of the i-th sealing section, the current glue output and the sealing size of the changing sealing area are input into a pre-constructed mathematical model to calculate the glue output adjustment amount of the glue dispenser; wherein the pre-constructed mathematical model is: ; Where: To adjust the amount of glue, is the current glue output, is the volume of the i-th sealed section, is the volume of the changing sealing area, Correction weights for volume ratios greater than zero, is the comprehensive weight factor; A time prediction module is used to obtain time prediction feature data, input the time prediction feature data into a preset time prediction model, and predict the future time point when the glue dispenser arrives at the changing sealing area; the time prediction feature data includes the current moving speed of the glue dispenser, the coordinate position of the changing sealing area, the coordinate position of the i-th sealing section, and the time point when the glue dispenser is in the i-th sealing section; The speed correction module is used to retrieve the current moving speed of the dispensing machine, combine the current moving speed, the glue output adjustment amount, the sealing size of the changed sealing area and the glue dispensing adjustment air pressure into the speed correction feature data, and input them into the preset speed change correction model to obtain the moving adjustment speed of the dispensing machine; The generation logic of the preset speed change correction model is as follows: Acquire historical movement speed correction training data, and divide the historical movement speed correction training data into a movement speed correction training set and a movement speed correction test set; the historical movement speed correction training data includes movement speed correction feature data and its corresponding movement adjustment speed; Constructing a second regression network, taking the speed correction feature data in the speed correction training set as the second regression network input data, taking the corresponding movement adjustment speed in the speed correction training set as the second regression network output data, training the second regression network, and obtaining an initial speed change correction network; The initial speed change correction network is tested using the speed correction test set, and the corresponding initial speed change correction network whose error is less than or equal to the preset second test error threshold is input as the preset speed change correction model; The logic for determining the movement adjustment speed in the historical movement speed correction training data is as follows: a1: When the changed sealing area is determined and the dispensing machine is used to dispense glue to the changed sealing area according to the air pressure adjusted by the dispensing, the current moving speed v of the dispensing machine is obtained; a2: Adjust the value of the current moving speed v to obtain the adjusted moving speed Q, where both v and Q are integers greater than zero; a3: subdivide the variable sealing area into G sealing subsections, and measure the actual glue coating thickness of each sealing subsection after dispensing according to the adjustment of the moving speed Q and the dispensing adjustment air pressure, where G is an integer greater than zero; a4: extract the standard glue coating thickness, calculate the uniformity coefficient according to the actual glue coating thickness and the standard glue coating thickness, compare the uniformity coefficient with the uniformity coefficient threshold, if the uniformity coefficient is greater than or equal to the uniformity coefficient threshold, return to step a2; if the uniformity coefficient is less than the uniformity coefficient threshold, adjust the moving speed Q as the moving adjustment speed; a5: Repeat the above steps a2 to a4 until the moving adjustment speed is obtained, and then end the loop; The adaptive control module is used to automatically control the dispensing machine based on the dispensing adjustment air pressure and the movement adjustment speed when it is at a future time point.
2. The adaptive dispensing machine control system based on sensor feedback according to claim 1 is characterized in that: The determining whether the (i+r)th sealing section is a variable sealing area comprises: Extracting the regional image of the i+rth sealed section, and calling the regional image of the ikth sealed section, where k is an integer greater than zero; Mark the regional image of the i+rth sealed section as a comparison image, and use the regional image of the ikth sealed section as a reference image; The pixel areas of the sealed sections in the comparison image and the reference image are respectively obtained by an image processing algorithm; using the pixel area of the sealed section in the comparison image as the comparison pixel area, and using the pixel area of the sealed section in the reference image as the reference pixel area; The comparison pixel area and the reference pixel area are numerically compared. If the values of the comparison pixel area and the reference pixel area are equal, the i+rth sealing segment is determined to be a non-changing sealing area; if the values of the comparison pixel area and the reference pixel area are not equal, the i+rth sealing segment is determined to be a changing sealing area.
3. The adaptive dispensing machine control system based on sensor feedback according to claim 2 is characterized in that: After determining whether the i+rth sealing section is a variable sealing area, the method includes: If the i+rth sealing section is determined to be a non-changing sealing area, r=r+1 is set and the data acquisition module is returned.
4. The adaptive dispensing machine control system based on sensor feedback according to claim 3 is characterized in that: The sealing dimensions include the actual length of the sealing area, the actual width of the sealing area, and the actual depth of the sealing area.
5. The adaptive dispensing machine control system based on sensor feedback according to claim 4 is characterized in that: The generation logic of the preset time prediction model is as follows: Obtaining historical dispensing machine time training data, and dividing the historical dispensing machine time training data into a time prediction training set and a time prediction test set; the historical dispensing machine time training data includes time prediction feature data and its corresponding future time point; Constructing a first regression network, taking the time prediction feature data in the time prediction training set as the first regression network input data, taking the corresponding future time point in the time prediction training set as the first regression network output data, training the first regression network, and obtaining an initial time prediction network; The initial time prediction network is tested using the time prediction test set, and the corresponding initial time prediction network with a value less than or equal to a preset first test error threshold is input as the preset time prediction model.
