An intelligent monitoring system for an electric fluid nozzle control mechanism

Abstract

The present invention discloses an intelligent monitoring system for an electric fluid nozzle control mechanism, and belongs to the technical field of electro-jet printing. Before starting to print, the present invention uses an angle detection module to detect the angle between the current nozzle axis and the Z axis, and determines the rotation direction of the nozzle axis during angle correction, and then corrects the angle of the nozzle axis according to the above angle and rotation direction, and then uses a spacing detection module to detect the spacing between the current nozzle end and the upper end of the collection plate after completing the angle correction work, and then corrects the position of the nozzle on the Z axis according to the spacing, thereby realizing the monitoring and management of the Z axis control mechanism of the electric fluid nozzle; when performing formal printing, the thickness detection module is used to detect the coverage thickness characterization data formed by the current droplet in real time, and then the pressure adjustment module is used to adjust the injection pressure generated by the injection pump, thereby realizing the monitoring and management of the solution pressurizing mechanism of the electric fluid nozzle; thereby further improving the printing quality.

Description

Technical Field

[0001] The invention relates to the technical field of electrojet printing, and in particular to an intelligent monitoring system for an electrofluid nozzle control mechanism. Background Art

[0002] Electrojet printing belongs to the field of electro-hydraulic coupling technology. The essence of its principle is to directly convert electrical energy into kinetic energy and use electric field to induce fluid movement. Electrojet printing uses high-voltage pulse electric field to "pull" the fluid out of the nozzle to obtain droplets on the collection plate. The pulse voltage is generated by a combination of a signal generator and a high-voltage amplifier. By setting the output waveform of the signal generator, the signal is connected to the high-voltage amplifier, and a high-voltage signal can be generated through the high-voltage amplifier. The collection plate is conductive glass, placed on the X and Y axes, and a negative DC high-voltage power supply is connected to the collection plate. A square wave is generated by a signal generator, and a high-voltage pulse is generated after passing through the high-voltage amplifier. It is connected to the nozzle by a wire, where the nozzle is located on the Z axis, and the solution in the nozzle is injected by a syringe pump under pressure. An electric field is formed between the nozzle and the collecting plate. As the voltage increases, the meniscus at the nozzle is affected by the electric field force to form a Taylor cone. When the high-voltage pulse exceeds the critical condition, the surface tension and electric field force at the nozzle are broken, and droplets are ejected from the "Taylor cone" to form a jet, which drips onto the base plate at the upper end of the collecting plate to form droplets. After the electrospray printing is completed, the target pattern is formed on the base plate. The working modes of electrospray printing are mainly divided into continuous spraying and point spraying modes. The continuous spraying mode is to continuously spray on the base plate at the upper end of the collecting plate, and the point spraying mode is to perform discontinuous spraying on the base plate at the upper end of the collecting plate.

[0003] In electrojet printing, when the distance between the nozzle and the substrate and the angle between the nozzle and the Z axis deviate, the printing quality will be greatly reduced. When the pressure applied by the injection pump deviates, the thickness of the coverage formed by the droplets on the substrate will be uneven, which will also reduce the printing quality. How to further improve the printing quality is an urgent problem to be solved. To this end, an intelligent supervision system for an electrofluidic nozzle control mechanism is proposed. Summary of the invention

[0004] The technical problem to be solved by the present invention is: how to improve the printing quality by correcting the nozzle position and adjusting the injection pump pressure, and provides an intelligent monitoring system for an electric fluid nozzle control mechanism.

[0005] The present invention solves the above technical problems through the following technical solutions, and the present invention includes an angle detection module, an angle correction module, a spacing detection module, a spacing correction module, a thickness detection module and a pressure adjustment module;

[0006] The angle detection module is used to detect the angle J between the current nozzle axis and the Z axis using a detection whiteboard before starting printing, and to determine the rotation direction of the nozzle axis during angle correction;

[0007] The angle correction module is used to correct the position of the nozzle axis according to the angle J between the current nozzle axis and the Z axis and the rotation direction of the nozzle axis during angle correction;

[0008] The distance detection module is used to detect the distance D1 between the current nozzle end and the upper end of the collecting plate after the angle correction work is completed;

[0009] The spacing correction module is used to correct the position of the nozzle on the Z axis according to the spacing D1 between the current nozzle end and the upper end of the collecting plate;

[0010] The thickness detection module is used to detect the coverage thickness characterization data formed by the current droplets in real time during formal printing;

[0011] The pressure regulating module is used to regulate the injection pressure generated by the injection pump according to the coverage thickness characterization data currently formed by the microdroplets.

[0012] Furthermore, the angle detection module includes a first coverage surface overhead image acquisition unit, a first coverage surface overhead image processing unit, and an angle acquisition unit; the first coverage surface overhead image acquisition unit is used to acquire a first coverage surface overhead image for detecting the formation of a single droplet on the whiteboard; the first coverage surface overhead image processing unit is used to process the first coverage surface overhead image to acquire angle characterization data and rotation direction data; the angle acquisition unit is used to acquire an angle J between the nozzle axis and the Z axis according to the angle characterization data;

[0013] The specific processing process of the first coverage surface overhead image processing unit is as follows:

[0014] S11: Binarization is performed on the overhead image of the first coverage surface, wherein the pixel values ​​of the white pixels on the detection whiteboard are set to 0, and the pixel values ​​of the color pixels of the coverage surface of the droplet are set to 1, thereby obtaining an area with all pixel values ​​of 1, that is, obtaining a first coverage area formed by a single droplet;

[0015] S12: using the contour detection function in OpenCV to identify the outer contour of the first coverage area, and obtaining the first outer contour line and the pixel coordinates of each point on the outer contour line;

[0016] S13: Calculate the two points on the first outer contour line that are farthest from each other according to the pixel coordinates of each point on the first outer contour line, and record them as A1 and A2;

[0017] S14: Take the midpoint of the line segment A1A2 as Ac, draw a perpendicular line to the line segment A1A2 through point Ac, and intersect the first outer contour line at points A3 and A4. At this time, the line segment A1A2 is not considered, and the first outer contour line area is divided into two areas by the line segment A3A4, that is, the first coverage area is divided into two areas, and the pixel areas of the two areas are calculated respectively, and it is determined whether the points A1 and A2 are respectively in the larger area or in the smaller area;

[0018] S15: Calculate the length of line segment A1A2 according to the pixel coordinates, recorded as L1; and determine the rotation direction of the nozzle axis during angle correction. When A2 is in a larger area and A1 is in a smaller area, the rotation direction of the nozzle axis is along the vector When A1 is in a larger area and A2 is in a smaller area, the rotation direction of the nozzle axis is along the vector The direction of movement, vector , The direction of is represented by the angle between it and the positive direction of the x-axis; wherein the length L1 is the angle characterizing the data;

[0019] The specific processing process of the angle acquisition unit is as follows: obtain the length L1, search and compare in the preset length-angle database, and obtain the angle value J corresponding to the current length L1, wherein the length-angle database stores the corresponding relationship between the length L1 and the angle value J.

[0020] Furthermore, the specific processing process of the angle correction module is as follows:

[0021] S21: Obtain the rotation direction of the nozzle axis during angle correction, and obtain the angle J between the current nozzle axis and the Z axis, that is, the angle at which the nozzle axis needs to rotate along the rotation direction;

[0022] S22: According to the acquired rotation direction and the angle required to rotate along the rotation direction, the Z-axis control mechanism is used to control the rotation of the nozzle, thereby completing the correction of the nozzle axis.

[0023] Furthermore, the spacing detection module includes a second coverage surface overhead image acquisition unit, a second coverage surface overhead image processing unit, and a spacing acquisition unit; the second coverage surface overhead image acquisition unit is used to acquire a second coverage surface overhead image for detecting the formation of a single droplet on the whiteboard; the second coverage surface overhead image processing unit is used to process the second coverage surface overhead image to acquire spacing representation data; the spacing acquisition unit is used to acquire the spacing D1 between the nozzle end and the upper end of the collecting plate according to the spacing representation data;

[0024] The specific processing process of the second coverage surface overhead image processing unit is as follows:

[0025] S31: Binarization processing is performed on the overhead image of the second coverage surface, wherein the pixel values ​​of the white pixels on the detection whiteboard are set to 0, and the pixel values ​​of the color pixels of the coverage surface of the droplet are set to 1, thereby obtaining an area with all pixel values ​​of 1, that is, obtaining the second coverage area formed by a single droplet;

[0026] S32: using the contour detection function in OpenCV to identify the outer contour of the second coverage area, and obtaining the second outer contour line and the pixel coordinates of each point on the outer contour line;

[0027] S33: Count the number of all pixel points inside the second outer contour line, recorded as I1, to obtain spacing representation data;

[0028] The specific processing process of the spacing acquisition unit is as follows: obtain the number of pixel points I1, search and compare in the preset pixel number-spacing database, and obtain the spacing D1 corresponding to the current number of pixel points I1, wherein the pixel number-spacing stores the corresponding relationship between the range of the pixel number I1 and the spacing D1.

[0029] Furthermore, the specific processing process of the spacing correction module is as follows:

[0030] S41: Obtaining the distance D1 between the current nozzle end and the upper end of the collecting plate;

[0031] S42: Obtaining the distance D between the nozzle end and the upper end of the collecting plate set during printing;

[0032] S43: Subtract the spacing D1 from the spacing D to obtain the spacing difference D2. According to the spacing difference D2, the Z-axis control mechanism is used to control the nozzle to move along the Z-axis. The moving distance is the absolute value of D2, thereby completing the position correction of the nozzle on the Z-axis.

[0033] Furthermore, in step S43, when the distance difference D2 is a negative value, the nozzle is moved in a direction close to the collecting plate, and when the distance difference D2 is a positive value, the nozzle is moved in a direction away from the collecting plate.

[0034] Furthermore, the thickness detection module includes a coverage surface overhead depth image acquisition unit and a coverage surface thickness calculation unit; the coverage surface overhead depth image acquisition unit is used to acquire a coverage surface overhead depth image formed by the current droplet on the substrate in real time; the coverage surface thickness calculation unit is used to calculate a coverage surface thickness representation value formed by the current droplet according to the coverage surface overhead depth image;

[0035] The specific processing process of the coverage thickness calculation unit is as follows:

[0036] S51: Detect and identify the coverage area in the coverage area overhead depth image using the trained target detection model, and obtain a third coverage area detection frame and coordinates of the upper left corner point and the lower right corner point of the detection frame;

[0037] S52: using the contour detection function in OpenCV to perform outer contour recognition on the coverage area inside the third coverage area detection frame, and obtaining the third outer contour line and the pixel coordinates of each point on the outer contour line;

[0038] S53: Calculate the center point of the detection frame according to the coordinates of the upper left corner point and the lower right corner point of the third coverage area detection frame, and record it as the center point C;

[0039] S54: Divide the third coverage area detection frame into four rectangles through the center point C, and divide the third coverage area into four sector areas. The four sector areas are recorded as areas R1, R2, R3, and R4 in a clockwise direction from the upper left.

[0040] S55: Counting the pixel values ​​of each pixel point inside the regions R1, R2, R3, and R4, that is, the depth values, and calculating the average value of the pixel values ​​of all the pixel points inside each sector region, which are recorded as R1avg, R2avg, R3avg, and R4avg respectively;

[0041] S56: Compare the pixel values ​​of each pixel point in the regions R1, R2, R3, and R4 with R1avg, R2avg, R3avg, and R4avg respectively. When the difference between the pixel value of a pixel point and the average value of the pixel value of the corresponding sector-shaped region exceeds a set threshold, delete the pixel point from the corresponding sector-shaped region.

[0042] S57: Counting the pixel values ​​of each pixel point retained in the regions R1, R2, R3, and R4 again, and calculating the average pixel values ​​of all pixel points retained in each sector region again, and recording them as R1avg', R2avg', R3avg', and R4avg' respectively;

[0043] S58: Calculate the weighted average of R1avg', R2avg', R3avg', and R4avg' according to the formula, which is used as the characterization value Fh of the coverage thickness formed by the current droplet. The calculation formula is as follows:

[0044] Fh=W1*R1avg'+W2*R2avg'+W3*R3avg'+W4*R4avg',

[0045] Among them, W1, W2, W3, and W4 are the weight proportions of the average pixel values ​​of all pixels retained inside the corresponding sector-shaped areas in the coverage thickness Fh. The values ​​of W1, W2, W3, and W4 are positively correlated with the number of pixels retained inside each sector-shaped area, and the sum of W1, W2, W3, and W4 is 1.

[0046] Furthermore, the specific processing process of the pressure regulating module is as follows:

[0047] S61: obtaining a coverage thickness characterization value Fh formed by the current droplet, and obtaining a preset threshold value Fs of the coverage thickness characterization value;

[0048] S62: subtracting a set threshold Fs from the coverage thickness characterization value Fh to obtain a difference value Fc;

[0049] S63: Search and compare in the preset difference-pressure adjustment amount database to obtain the pressure adjustment amount Pt corresponding to the current difference Fc, and use the pressure adjustment amount Pt to adjust the injection pressure Pn generated by the current injection pump, wherein the difference-pressure adjustment amount database stores the corresponding relationship between the difference Fc range and the pressure adjustment amount Pt.

[0050] Furthermore, in step S63, when Fc is a positive value, the injection pressure generated by the injection pump during the next droplet printing is obtained by subtracting the pressure adjustment amount Pt from the injection pressure Pn. Conversely, when Fc is a negative value, the injection pressure generated by the injection pump during the next droplet printing is obtained by adding the pressure adjustment amount Pt to the injection pressure Pn.

[0051] Compared with the prior art, the present invention has the following advantages: the intelligent monitoring system of the electric fluid nozzle control mechanism, before starting printing, uses an angle detection module to detect the angle between the current nozzle axis and the Z axis, and determines the rotation direction of the nozzle axis during angle correction, and then uses the angle correction module to correct the angle of the nozzle axis according to the above angle and rotation direction, and then uses the spacing detection module to detect the spacing between the current nozzle end and the upper end of the collection plate after completing the angle correction work, and then uses the spacing to correct the position of the nozzle on the Z axis, thereby realizing the monitoring and management of the Z-axis control mechanism of the electric fluid nozzle; when performing formal printing, uses the thickness detection module to detect the coverage thickness characterization data formed by the current droplets in real time, and then uses the pressure adjustment module to adjust the injection pressure generated by the injection pump, thereby realizing the monitoring and management of the solution pressurizing mechanism of the electric fluid nozzle. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a structural schematic diagram of an intelligent monitoring system of an electric fluid nozzle control mechanism in an embodiment of the present invention;

[0053] Figure 2 Schematic diagram of the positions of the syringe pump, nozzle and other components in the embodiment of the present invention (side view), wherein 1 is the syringe pump, 2 is the nozzle, 3 is the collection plate, and 4 is the base plate / detection white plate;

[0054] Figure 3 is a schematic diagram of a first coverage overhead image for detecting a single droplet formed on a whiteboard in an embodiment of the present invention;

[0055] Figure 4 is a schematic diagram of a second coverage surface overhead image for detecting a single droplet formed on a whiteboard in an embodiment of the present invention;

[0056] Figure 5 1 is a schematic diagram of a top-down depth image of the coverage area formed by the current droplets on the substrate plate in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0058] like Figure 1 As shown, this embodiment provides a technical solution: an intelligent monitoring system for an electric fluid nozzle control mechanism. In this embodiment, the electric fluid nozzle adopts a point spraying mode, including an angle detection module, an angle correction module, a spacing detection module, a spacing correction module, a thickness detection module and a pressure adjustment module;

[0059] In this embodiment, the angle detection module is used to detect the angle J between the current nozzle axis and the Z axis using a detection whiteboard before starting printing, and determine the rotation direction of the nozzle axis during angle correction;

[0060] To be more specific, the angle detection module includes a first coverage surface overhead image acquisition unit, a first coverage surface overhead image processing unit, and an angle acquisition unit; the first coverage surface overhead image acquisition unit is used to acquire a first coverage surface overhead image formed to detect a single droplet on the whiteboard; the first coverage surface overhead image processing unit is used to process the first coverage surface overhead image to acquire angle characterization data and rotation direction data; the angle acquisition unit is used to acquire an angle J between the nozzle axis and the Z axis based on the angle characterization data.

[0061] To be more specific, the first coverage surface overhead image acquisition unit is an industrial camera, the optical axis of the industrial camera is perpendicular to the surface of the detection whiteboard, and the detection whiteboard is arranged parallel to the collecting plate at its lower end, the x and y axes of the first coverage surface overhead image are respectively parallel to the X and Y axes of the collecting plate and have the same direction, and the position and specifications of the detection whiteboard and the base plate during printing are the same.

[0062] It should be noted that, when in the correct position, the nozzle axis should coincide with the Z-axis position.

[0063] As more specific, the specific processing process of the first coverage surface overhead image processing unit (see Figure 3 )as follows:

[0064] S11: Binarization is performed on the overhead image of the first coverage surface, wherein the pixel values ​​of the white pixels on the detection whiteboard are set to 0, and the pixel values ​​of the color pixels of the coverage surface of the droplet are set to 1, thereby obtaining an area with all pixel values ​​of 1, that is, obtaining a first coverage area formed by a single droplet;

[0065] S12: using the contour detection function in OpenCV to identify the outer contour of the first coverage area, and obtaining the first outer contour line and the pixel coordinates of each point on the outer contour line;

[0066] S13: Calculate the two points on the first outer contour line that are farthest from each other according to the pixel coordinates of each point on the first outer contour line, and record them as A1 and A2;

[0067] S14: Take the midpoint of the line segment A1A2 as Ac, draw a perpendicular line to the line segment A1A2 through point Ac, and intersect the first outer contour line at points A3 and A4. At this time, the line segment A1A2 is not considered, and the first outer contour line area is divided into two areas by the line segment A3A4, that is, the first coverage area is divided into two areas, and the pixel areas of the two areas are calculated respectively, and it is determined whether the points A1 and A2 are respectively in the larger area or the smaller area;

[0068] S15: Calculate the length of line segment A1A2 according to the pixel coordinates, recorded as L1; and determine the rotation direction of the nozzle axis during angle correction. When A2 is in a larger area and A1 is in a smaller area, the rotation direction of the nozzle axis is along the vector When A1 is in a larger area and A2 is in a smaller area, the rotation direction of the nozzle axis is along the vector The direction of movement, vector , The direction of is represented by the angle between it and the positive direction of the x-axis; wherein the length L1, i.e. the angle, represents the data.

[0069] Through the above process, the angle J between the current nozzle axis and the Z axis can be accurately obtained, and the rotation direction of the nozzle axis during angle correction can be determined.

[0070] It should be noted that when there is a certain angle between the current nozzle axis and the Z axis, the first coverage shape formed by a single droplet on the whiteboard is detected as follows: Figure 3 shown.

[0071] To be more specific, the specific processing process of the angle acquisition unit is as follows: obtain the length L1, search and compare in the preset length-angle database, and obtain the angle value J corresponding to the current length L1, wherein the length-angle database stores the correspondence between the length L1 and the angle value J.

[0072] In this embodiment, the angle correction module is used to perform position correction on the nozzle axis according to the angle J between the current nozzle axis and the Z axis and the rotation direction of the nozzle axis during angle correction;

[0073] More specifically, the specific processing process of the angle correction module is as follows:

[0074] S21: Obtain the rotation direction of the nozzle axis during angle correction, and obtain the angle J between the current nozzle axis and the Z axis, that is, the angle at which the nozzle axis needs to rotate along the rotation direction;

[0075] S22: According to the acquired rotation direction and the angle required to rotate along the rotation direction, the Z-axis control mechanism is used to control the rotation of the nozzle, thereby completing the correction of the nozzle axis.

[0076] It should be noted that, in this embodiment, the Z-axis control mechanism drives the injection pump and the nozzle connected thereto to rotate simultaneously.

[0077] In this embodiment, the distance detection module is used to detect the distance D1 between the current nozzle end and the upper end of the collecting plate after completing the angle correction work;

[0078] To be more specific, the spacing detection module includes a second coverage surface overhead image acquisition unit, a second coverage surface overhead image processing unit, and a spacing acquisition unit; the second coverage surface overhead image acquisition unit is used to acquire a second coverage surface overhead image formed to detect a single droplet on the whiteboard; the second coverage surface overhead image processing unit is used to process the second coverage surface overhead image to acquire spacing characterization data; the spacing acquisition unit is used to acquire the spacing D1 between the nozzle end and the upper end of the collection plate according to the spacing characterization data.

[0079] It should be noted that the second coverage surface overhead image acquisition unit is an industrial camera that serves as the first coverage surface overhead image acquisition unit. Due to the different process positions, it is referred to as the "second coverage surface overhead image acquisition unit" for the convenience of distinction. Therefore, the x and y axes of the second coverage surface overhead image are respectively parallel to the X and Y axes of the collection plate and have the same direction.

[0080] As more specific, the specific processing process of the second coverage surface overhead image processing unit (see Figure 4 )as follows:

[0081] S31: Binarization processing is performed on the overhead image of the second coverage surface, wherein the pixel values ​​of the white pixels on the detection whiteboard are set to 0, and the pixel values ​​of the color pixels of the coverage surface of the droplet are set to 1, thereby obtaining an area with all pixel values ​​of 1, that is, obtaining the second coverage area formed by a single droplet;

[0082] S32: using the contour detection function in OpenCV to identify the outer contour of the second coverage area, and obtaining the second outer contour line and the pixel coordinates of each point on the outer contour line;

[0083] S33: Count the number of all pixel points inside the second outer contour line, recorded as I1, to obtain spacing representation data.

[0084] Through the above process, the spacing characterization data can be accurately obtained, which is convenient for the subsequent spacing correction work.

[0085] To be more specific, the specific processing process of the spacing acquisition unit is as follows: obtain the number of pixel points I1, search and compare in the preset pixel number-spacing database, and obtain the spacing D1 corresponding to the current number of pixel points I1, wherein the pixel number-spacing stores the correspondence between the range of the pixel number I1 and the spacing D1.

[0086] It should be noted that after the angle correction is completed, the first coverage shape formed by a single droplet on the whiteboard is detected as follows: Figure 4 As shown, it can be regarded as a circle.

[0087] In this embodiment, the spacing correction module is used to correct the position of the nozzle on the Z axis according to the spacing D1 between the current nozzle end and the upper end of the collecting plate.

[0088] More specifically, the specific processing process of the spacing correction module is as follows:

[0089] S41: Obtaining the distance D1 between the current nozzle end and the upper end of the collecting plate;

[0090] S42: Obtaining the distance D between the nozzle end and the upper end of the collecting plate set during printing;

[0091] S43: Subtract the spacing D1 from the spacing D to obtain the spacing difference D2, and use the Z-axis control mechanism to control the nozzle to move up and down along the Z-axis according to the spacing difference D2, thereby completing the position correction of the nozzle on the Z-axis.

[0092] More specifically, in step S43, when the distance difference D2 is a negative value, it indicates that the nozzle should move downward, and when the distance difference D2 is a positive value, it indicates that the nozzle should move upward.

[0093] In this embodiment, before starting printing, the angle detection module is used to detect the angle between the current nozzle axis and the Z axis, and to determine the rotation direction of the nozzle axis during angle correction. The angle correction module is then used to correct the angle of the nozzle axis according to the above angle and rotation direction. After the angle correction is completed, the spacing detection module is used to detect the spacing between the current nozzle end and the upper end of the collection plate. The spacing is then used to correct the position of the nozzle on the Z axis, thereby realizing the monitoring and management of the Z-axis control mechanism of the electrofluid nozzle.

[0094] In this embodiment, the thickness detection module is used to detect the coverage thickness characterization data formed by the current droplets in real time during formal printing;

[0095] More specifically, the thickness detection module includes a coverage surface overhead depth image acquisition unit and a coverage surface thickness calculation unit; the coverage surface overhead depth image acquisition unit is used to acquire in real time the coverage surface overhead depth image formed by the current droplets on the substrate plate; the coverage surface thickness calculation unit is used to calculate a coverage surface thickness characterization value formed by the current droplets based on the coverage surface overhead depth image.

[0096] It should be noted that the coverage surface overhead depth image acquisition unit is a depth camera. When shooting, the projection point of the optical axis of the depth camera on the base plate is the same as the projection point of the nozzle axis when printing the current droplet on the base plate. After each droplet is sprayed, the position of the collection plate is moved so that the current droplet on the base plate is directly below the depth camera, and then the picture is taken. Similarly, the x and y axes of the coverage surface overhead depth image are parallel to the x and y axes of the collection plate and in the same direction.

[0097] More specifically, the specific processing process of the coverage thickness calculation unit (see Figure 5 )as follows:

[0098] S51: Detect and identify the coverage area in the coverage area overhead depth image using the trained target detection model, and obtain a third coverage area detection frame and coordinates of the upper left corner point and the lower right corner point of the detection frame;

[0099] S52: using the contour detection function in OpenCV to perform outer contour recognition on the coverage area inside the third coverage area detection frame, and obtaining the third outer contour line and the pixel coordinates of each point on the outer contour line;

[0100] S53: Calculate the center point of the detection frame according to the coordinates of the upper left corner point and the lower right corner point of the third coverage area detection frame, and record it as the center point C;

[0101] S54: Divide the third coverage area detection frame into four rectangles through the center point C, and divide the third coverage area into four sector areas. The four sector areas are recorded as areas R1, R2, R3, and R4 in a clockwise direction from the upper left.

[0102] S55: Counting the pixel values ​​of each pixel point inside the regions R1, R2, R3, and R4, that is, the depth values, and calculating the average value of the pixel values ​​of all the pixel points inside each sector region, which are recorded as R1avg, R2avg, R3avg, and R4avg respectively;

[0103] S56: Compare the pixel values ​​of each pixel point in the regions R1, R2, R3, and R4 with R1avg, R2avg, R3avg, and R4avg respectively. When the difference between the pixel value of a pixel point and the average value of the pixel value of the corresponding sector-shaped region exceeds a set threshold, delete the pixel point from the corresponding sector-shaped region.

[0104] S57: Count the pixel values ​​of each pixel point retained in the regions R1, R2, R3, and R4 again, that is, the depth value, and calculate the average value of the pixel values ​​of all the pixel points retained in each sector region again, which are recorded as R1avg', R2avg', R3avg', and R4avg' respectively;

[0105] S58: Calculate the weighted average of R1avg', R2avg', R3avg', and R4avg' according to the formula, which is used as the characterization value Fh of the coverage thickness formed by the current droplet. The calculation formula is as follows:

[0106] Fh=W1*R1avg'+W2*R2avg'+W3*R3avg'+W4*R4avg',

[0107] Among them, W1, W2, W3, and W4 are the weight proportions of the average pixel values ​​of all pixels retained in the corresponding sector area in the coverage thickness Fh. The values ​​of W1, W2, W3, and W4 are positively correlated with the number of pixels retained in each sector area, that is, the more pixels are retained in the sector area, the greater the weight proportion of the corresponding sector area. The sum of W1, W2, W3, and W4 is 1, and the specific value is set according to the actual application.

[0108] To be more specific, the object detection model is trained based on the Yolo V5s object detection network.

[0109] In the present invention, relevant depth value data in the image is cleverly used to characterize the coverage thickness formed by the current droplet, so that the basis for subsequent pressure adjustment is more accurate, and the printing quality is further improved.

[0110] In this embodiment, the pressure regulating module is used to regulate the injection pressure generated by the injection pump according to the characterization data of the coverage thickness formed by the current droplets;

[0111] As more specific, the specific processing process of the pressure regulating module is as follows:

[0112] S61: obtaining a coverage thickness characterization value Fh formed by the current droplet, and obtaining a preset threshold value Fs of the coverage thickness characterization value;

[0113] S62: subtracting a set threshold Fs from the coverage thickness characterization value Fh to obtain a difference value Fc;

[0114] S63: Search and compare in the preset difference-pressure adjustment amount database to obtain the pressure adjustment amount Pt corresponding to the current difference Fc, and use the pressure adjustment amount Pt to adjust the injection pressure Pn generated by the current injection pump, thereby ensuring that the injection pressure of the next droplet is more accurate, making the uniformity of the thickness of the coverage surface of each droplet better, and ensuring the printing quality.

[0115] In step S63, the difference-pressure adjustment amount database stores the corresponding relationship between the difference Fc range and the pressure adjustment amount Pt. When Fc is a positive value, the injection pressure generated by the injection pump during the next droplet printing is obtained by subtracting the pressure adjustment amount Pt from the injection pressure Pn. On the contrary, when Fc is a negative value, the injection pressure generated by the injection pump during the next droplet printing is obtained by adding the pressure adjustment amount Pt to the injection pressure Pn. The greater the injection pressure generated by the injection pump, the smaller the droplet coverage thickness, and the smaller the injection pressure generated by the injection pump, the greater the droplet coverage thickness.

[0116] It should be noted that, in this embodiment, a single printing is performed using a detection whiteboard before starting printing, and the angle detection module is used to determine the angle J between the current nozzle axis and the Z axis, and to determine the rotation direction of the nozzle axis during angle correction. Then, the angle correction module is used to perform angle correction of the nozzle axis based on the above information. The detection whiteboard is used again for a single printing, and the spacing detection module is used to detect the spacing D1 between the current nozzle end and the upper end of the collecting plate after completing the angle correction. Then, the position of the nozzle on the Z axis is corrected based on the above information to complete the spacing correction. Finally, the base plate is placed on the collecting plate and formal printing begins. The thickness detection module is used to detect the coverage thickness characterization data formed by the current droplets in real time, and then, based on the coverage thickness characterization data, the pressure regulation module is used to adjust the injection pressure generated by the injection pump, thereby further improving the printing quality.

[0117] To sum up, the intelligent monitoring system of the electric fluid nozzle control mechanism of the above embodiment, before starting printing, uses the angle detection module to detect the angle between the current nozzle axis and the Z axis, and determines the rotation direction of the nozzle axis during angle correction, and then uses the angle correction module to correct the angle of the nozzle axis according to the above angle and rotation direction, and then uses the spacing detection module to detect the spacing between the current nozzle end and the upper end of the collecting plate after completing the angle correction work, and then uses the spacing to correct the position of the nozzle on the Z axis, thereby realizing the monitoring and management of the Z-axis control mechanism of the electric fluid nozzle; when performing formal printing, the thickness detection module is used to detect the coverage thickness characterization data formed by the current droplets in real time, and then the pressure regulation module is used to adjust the injection pressure generated by the injection pump, thereby realizing the monitoring and management of the solution pressurizing mechanism of the electric fluid nozzle.

[0118] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0119] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0120] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent monitoring system for an electric fluid nozzle control mechanism, characterized in that: It includes an angle detection module, an angle correction module, a spacing detection module, a spacing correction module, a thickness detection module and a pressure adjustment module; The angle detection module is used to detect the angle J between the current nozzle axis and the Z axis using a detection whiteboard before starting printing, and to determine the rotation direction of the nozzle axis during angle correction; The angle detection module includes a first coverage surface overhead image acquisition unit, a first coverage surface overhead image processing unit, and an angle acquisition unit; the first coverage surface overhead image acquisition unit is used to acquire a first coverage surface overhead image formed by a single droplet on the whiteboard; the first coverage surface overhead image processing unit is used to process the first coverage surface overhead image to acquire angle characterization data and rotation direction data; the angle acquisition unit is used to acquire an angle J between the nozzle axis and the Z axis according to the angle characterization data; The specific processing process of the first coverage surface overhead image processing unit is as follows: S11: Binarization is performed on the overhead image of the first coverage surface, wherein the pixel values ​​of the white pixels on the detection whiteboard are set to 0, and the pixel values ​​of the color pixels of the coverage surface of the droplet are set to 1, thereby obtaining an area with all pixel values ​​of 1, that is, obtaining a first coverage area formed by a single droplet; S12: using the contour detection function in OpenCV to identify the outer contour of the first coverage area, and obtaining the first outer contour line and the pixel coordinates of each point on the outer contour line; S13: Calculate the two points on the first outer contour line that are farthest from each other according to the pixel coordinates of each point on the first outer contour line, and record them as A1 and A2; S14: Take the midpoint of the line segment A1A2 as Ac, draw a perpendicular line to the line segment A1A2 through point Ac, and intersect the first outer contour line at points A3 and A4. At this time, the line segment A1A2 is not considered, and the first outer contour line area is divided into two areas by the line segment A3A4, that is, the first coverage area is divided into two areas, and the pixel areas of the two areas are calculated respectively, and it is determined whether the points A1 and A2 are respectively in the larger area or in the smaller area; S15: Calculate the length of line segment A1A2 according to the pixel coordinates, recorded as L1; and determine the rotation direction of the nozzle axis during angle correction. When A2 is in a larger area and A1 is in a smaller area, the rotation direction of the nozzle axis is along the vector When A1 is in a larger area and A2 is in a smaller area, the rotation direction of the nozzle axis is along the vector The direction of movement, vector , The direction of is represented by the angle between it and the positive direction of the x-axis; wherein the length L1 is the angle characterizing the data; The specific processing process of the angle acquisition unit is as follows: obtain the length L1, search and compare in a preset length-angle database, and obtain the angle value J corresponding to the current length L1, wherein the length-angle database stores the corresponding relationship between the length L1 and the angle value J; The angle correction module is used to correct the position of the nozzle axis according to the angle J between the current nozzle axis and the Z axis and the rotation direction of the nozzle axis during angle correction; The distance detection module is used to detect the distance D1 between the current nozzle end and the upper end of the collecting plate after the angle correction work is completed; The spacing correction module is used to correct the position of the nozzle on the Z axis according to the spacing D1 between the current nozzle end and the upper end of the collecting plate; The thickness detection module is used to detect the coverage thickness characterization data formed by the current droplets in real time during formal printing; The pressure regulating module is used to regulate the injection pressure generated by the injection pump according to the coverage thickness characterization data currently formed by the microdroplets.

2. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 1, characterized in that: The specific processing process of the angle correction module is as follows: S21: Obtain the rotation direction of the nozzle axis during angle correction, and obtain the angle J between the current nozzle axis and the Z axis, that is, the angle at which the nozzle axis needs to rotate along the rotation direction; S22: According to the acquired rotation direction and the angle required to rotate along the rotation direction, the Z-axis control mechanism is used to control the rotation of the nozzle, thereby completing the correction of the nozzle axis.

3. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 1, characterized in that: The spacing detection module includes a second coverage surface overhead image acquisition unit, a second coverage surface overhead image processing unit, and a spacing acquisition unit; the second coverage surface overhead image acquisition unit is used to acquire a second coverage surface overhead image for detecting the formation of a single droplet on the whiteboard; the second coverage surface overhead image processing unit is used to process the second coverage surface overhead image to acquire spacing representation data; the spacing acquisition unit is used to acquire the spacing D1 between the nozzle end and the upper end of the collecting plate according to the spacing representation data; The specific processing process of the second coverage surface overhead image processing unit is as follows: S31: Binarization processing is performed on the overhead image of the second coverage surface, wherein the pixel values ​​of the white pixels on the detection whiteboard are set to 0, and the pixel values ​​of the color pixels of the coverage surface of the droplet are set to 1, thereby obtaining an area with all pixel values ​​of 1, that is, obtaining the second coverage area formed by a single droplet; S32: using the contour detection function in OpenCV to identify the outer contour of the second coverage area, and obtaining the second outer contour line and the pixel coordinates of each point on the outer contour line; S33: Count the number of all pixel points inside the second outer contour line, recorded as I1, to obtain spacing representation data; The specific processing process of the spacing acquisition unit is as follows: obtain the number of pixel points I1, search and compare in the preset pixel number-spacing database, and obtain the spacing D1 corresponding to the current number of pixel points I1, wherein the pixel number-spacing stores the corresponding relationship between the range of the pixel number I1 and the spacing D1.

4. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 3, characterized in that: The specific processing process of the spacing correction module is as follows: S41: Obtaining the distance D1 between the current nozzle end and the upper end of the collecting plate; S42: Obtaining the distance D between the nozzle end and the upper end of the collecting plate set during printing; S43: Subtract the spacing D1 from the spacing D to obtain the spacing difference D2. According to the spacing difference D2, the Z-axis control mechanism is used to control the nozzle to move along the Z-axis. The moving distance is the absolute value of D2, thereby completing the position correction of the nozzle on the Z-axis.

5. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 4, characterized in that: In step S43, when the distance difference D2 is a negative value, the nozzle is moved toward the direction close to the collecting plate, and when the distance difference D2 is a positive value, the nozzle is moved away from the collecting plate.

6. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 3, characterized in that: The thickness detection module includes a coverage surface overhead depth image acquisition unit and a coverage surface thickness calculation unit; the coverage surface overhead depth image acquisition unit is used to acquire a coverage surface overhead depth image formed by the current droplets on the substrate in real time; the coverage surface thickness calculation unit is used to calculate the coverage surface thickness representation value formed by the current droplets according to the coverage surface overhead depth image; The specific processing process of the coverage thickness calculation unit is as follows: S51: Detect and identify the coverage area in the coverage area overhead depth image using the trained target detection model, and obtain a third coverage area detection frame and coordinates of the upper left corner point and the lower right corner point of the detection frame; S52: using the contour detection function in OpenCV to perform outer contour recognition on the coverage area inside the third coverage area detection frame, and obtaining the third outer contour line and the pixel coordinates of each point on the outer contour line; S53: Calculate the center point of the detection frame according to the coordinates of the upper left corner point and the lower right corner point of the third coverage area detection frame, and record it as the center point C; S54: Divide the third coverage area detection frame into four rectangles through the center point C, and divide the third coverage area into four sector areas. The four sector areas are recorded as areas R1, R2, R3, and R4 in a clockwise direction from the upper left. S55: Counting the pixel values ​​of each pixel point inside the regions R1, R2, R3, and R4, that is, the depth values, and calculating the average value of the pixel values ​​of all the pixel points inside each sector region, which are recorded as R1avg, R2avg, R3avg, and R4avg respectively; S56: Compare the pixel values ​​of each pixel point in the regions R1, R2, R3, and R4 with R1avg, R2avg, R3avg, and R4avg respectively. When the difference between the pixel value of a pixel point and the average value of the pixel value of the corresponding sector-shaped region exceeds a set threshold, delete the pixel point from the corresponding sector-shaped region. S57: Counting the pixel values ​​of each pixel point retained in the regions R1, R2, R3, and R4 again, and calculating the average pixel values ​​of all pixel points retained in each sector region again, and recording them as R1avg', R2avg', R3avg', and R4avg' respectively; S58: Calculate the weighted average of R1avg', R2avg', R3avg', and R4avg' according to the formula, which is used as the characterization value Fh of the coverage thickness formed by the current droplet. The calculation formula is as follows: Fh=W1*R1avg'+W2*R2avg'+W3*R3avg'+W4*R4avg' Among them, W1, W2, W3, and W4 are the weight proportions of the average pixel values ​​of all pixels retained inside the corresponding sector-shaped areas in the coverage thickness Fh. The values ​​of W1, W2, W3, and W4 are positively correlated with the number of pixels retained inside each sector-shaped area, and the sum of W1, W2, W3, and W4 is 1.

7. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 6, characterized in that: The specific processing process of the pressure regulation module is as follows: S61: obtaining a coverage thickness characterization value Fh formed by the current droplet, and obtaining a preset threshold value Fs of the coverage thickness characterization value; S62: subtracting a set threshold Fs from the coverage thickness characterization value Fh to obtain a difference value Fc; S63: Search and compare in the preset difference-pressure adjustment amount database to obtain the pressure adjustment amount Pt corresponding to the current difference Fc, and use the pressure adjustment amount Pt to adjust the injection pressure Pn generated by the current injection pump, wherein the difference-pressure adjustment amount database stores the corresponding relationship between the difference Fc range and the pressure adjustment amount Pt.

8. The intelligent monitoring system of an electric fluid nozzle control mechanism according to claim 7, characterized in that: In step S63, when Fc is a positive value, the injection pressure generated by the injection pump during the next droplet printing is obtained by subtracting the pressure adjustment amount Pt from the injection pressure Pn. Conversely, when Fc is a negative value, the injection pressure generated by the injection pump during the next droplet printing is obtained by adding the pressure adjustment amount Pt to the injection pressure Pn.

Images