Unity engine-based dispensing control method and system and electronic equipment

Abstract

The invention provides an adhesive dispensing control method and system based on a Unity engine and electronic equipment, which are applied to a virtual layer of the adhesive dispensing control system based on the Unity engine, and the virtual layer comprises an adhesive dispensing virtual model constructed based on the Unity engine. The method comprises the steps that when a rocker of the mechanical arm is pressed down, real-time pressure of a needle and distance information between the needle and a target point are obtained; obtaining prediction information based on the distance information between the needle head and the target point, the real-time pressure and a pre-constructed prediction model, and carrying out analogue simulation on the dispensing process based on the prediction information and the dispensing virtual model; wherein the prediction information at least comprises the width of the glue line and the predicted motion trail of the needle head; and generating a control signal based on the prediction information to enable the mechanical arm to control the movement of the needle based on the control signal. According to the invention, the reject ratio of dispensing and the damage to the chip are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of microelectronic packaging, in particular to a dispensing control method and system based on a Unity engine and electronic equipment. BACKGROUND

[0002] In the field of microelectronic packaging, the dispensing needle diameter has been reduced to the level of 50 μm. In the dispensing process, the dispensing failure rate caused by needle deformation accounts for 34% of the packaging defects. Every 10 μm of needle offset will cause wafer scrap loss. Therefore, the needle needs to be calibrated by a calibration system, and the existing calibration system needs to be manually maintained for an average of 2.7 hours per week. At present, in order to avoid downtime maintenance, the solutions adopted include: mechanical compensation, that is, using a spring damping structure to passively absorb vibration; optical detection, that is, using a high-speed CMOS camera to realize sub-pixel detection; digital twin, that is, importing a CAD model for offline simulation. However, mechanical compensation is only suitable for dispensing with a coarse pitch of more than 200 μm; the optical detection system causes compensation lag (12 ms) due to delay; the digital twin lacks real-time data closed loop (update period > 30 s). In summary, the existing calibration method is not effective. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a dispensing control method and system based on a Unity engine and electronic equipment to reduce the dispensing failure rate and damage to chips.

[0004] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: In a first aspect, the present application provides a dispensing control method based on a Unity engine, applied to a virtual layer of a dispensing control system based on a Unity engine, the virtual layer comprising a dispensing virtual model constructed based on a Unity engine; the method comprises: obtaining real-time pressure of a needle and distance information between the needle and a target point when a mechanical arm joystick is pressed; obtaining prediction information based on the distance information between the needle and the target point, the real-time pressure and a prediction model constructed in advance, and simulating a dispensing process based on the prediction information and the dispensing virtual model; wherein the prediction information at least includes: glue line width and predicted motion trajectory of the needle; generating a control signal based on the prediction information, so that the mechanical arm controls the motion of the needle based on the control signal.

[0005] Optionally, obtaining prediction information based on the distance information between the needle and the target point, the real-time pressure and the prediction model constructed in advance comprises: inputting the historical motion trajectory of the needle and the real-time pressure into a first prediction model constructed in advance to obtain the glue line width in a future preset time period; inputting the distance information between the needle and the target point into a second prediction model constructed in advance to obtain the predicted motion trajectory of the needle.

[0006] Optionally, based on the distance information between the needle and the target point, the real-time pressure and the pre-constructed prediction model, the prediction information is obtained, and the method further comprises: inputting the historical pressure information of the needle, the number of times of use and the real-time pressure into the pre-constructed third prediction model to obtain the remaining service life of the needle.

[0007] Optionally, the method further comprises: performing risk warning based on the prediction information.

[0008] Optionally, the risk warning based on the prediction information comprises: controlling the movement of the needle based on the predicted movement trajectory of the needle, and acquiring a real-time movement distance of the needle during the movement of the needle; comparing the real-time movement distance of the needle with a pre-set distance threshold, and generating risk warning information based on the comparison result.

[0009] Optionally, the risk warning information generated based on the comparison result comprises: when the real-time movement distance of the needle is greater than or equal to a first distance threshold, generating first risk warning information and reducing the movement speed of the needle to a pre-set value; when the real-time movement distance of the needle is greater than or equal to a second distance threshold, generating second risk warning information; and when the real-time movement distance of the needle is greater than or equal to a third distance threshold, generating third risk warning information and stopping the movement of the needle and cutting off the supply of the air source for dispensing.

[0010] Optionally, the risk warning based on the prediction information further comprises: when the remaining service life of the needle is less than a pre-set service life threshold, generating first risk warning information; determining a trajectory deviation value based on the predicted movement trajectory of the needle, and generating the first risk warning information when the trajectory deviation value exceeds a pre-set trajectory deviation threshold; and when the real-time pressure exceeds a pre-set pressure threshold, generating fourth risk warning information.

[0011] In a second aspect, the present application provides a dispensing control system based on a Unity engine, comprising: a physical layer, a virtual layer and a control layer; the physical layer comprises a mechanical arm and a pressure sensor, which are used to collect real-time pressure of a needle and distance information between the needle and a target point, and send the real-time pressure and the distance information between the needle and the target point to the virtual layer; the virtual layer comprises a dispensing virtual model constructed based on a Unity engine, which is used to predict and simulate a model of a dispensing process by using any one of the dispensing control methods based on a Unity engine provided in the first aspect, and generate a control signal; and the control layer is used to send the control signal to the mechanical arm, so that the mechanical arm controls the movement of the needle based on the control signal.

[0012] In a third aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement the steps of any one of the methods provided in the first aspect.

[0013] In a fourth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is run by a processor to execute the steps of the method of any one of the first aspect.

[0014] The present application has the following beneficial effects: The above-mentioned dispensing control method, system and electronic device based on the Unity engine provided by the present application are applied to a virtual layer of a dispensing control system based on the Unity engine, and the virtual layer includes a dispensing virtual model constructed based on the Unity engine. The method includes: obtaining real-time pressure of a needle and distance information between the needle and a target point when a mechanical arm joystick is pressed down; obtaining prediction information based on the distance information between the needle and the target point, the real-time pressure and a pre-constructed prediction model, and simulating a dispensing process based on the prediction information and the dispensing virtual model; wherein the prediction information at least includes a glue line width and a predicted motion trajectory of the needle; and generating a control signal based on the prediction information, so that the mechanical arm controls the motion of the needle based on the control signal. In the above-mentioned method, the dispensing process can be predicted based on the Unity engine and the pre-constructed prediction model, and the dispensing process can be simulated through the dispensing virtual model, so that the motion of the needle can be adjusted in time according to the prediction information and the dispensing result, and the dispensing failure rate and damage to the chip are reduced.

[0015] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and achieved by the structure particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following will be described in detail in combination with the preferred embodiments and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0018] Figure 1 A flowchart of a dispensing control method based on the Unity engine provided by an embodiment of the present application; Figure 2 A schematic diagram of a dispensing control system based on the Unity engine provided by an embodiment of the present application; Figure 3 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described below in detail with reference to the drawings. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0020] At present, the adopted point glue calibration method includes: mechanical compensation, that is, passively absorbing vibration by using spring damping structure; optical detection, that is, realizing sub-pixel detection by using a high-speed CMOS camera; digital twin, that is, introducing a CAD model for offline simulation. However, the mechanical compensation is only applicable to point glue with a coarse pitch greater than 200 μm; the optical detection system delay leads to compensation lag (12 ms); the digital twin lacks real-time data closed loop (update period > 30 s). In summary, the existing calibration method has poor effect.

[0021] Based on this, the point glue control method, system and electronic device based on the Unity engine provided by the embodiments of the present application can reduce the point glue failure rate and damage to the chip.

[0022] In order to facilitate the understanding of the embodiments, first, a point glue control system based on the Unity engine disclosed by the embodiments of the present application is introduced in detail. The system includes a physical layer, a virtual layer and a control layer. The physical layer includes a mechanical arm and a pressure sensor, which is used to collect real-time pressure of the needle and distance information between the needle and the target point, and send the real-time pressure and the distance information between the needle and the target point to the virtual layer. The virtual layer includes a point glue virtual model constructed based on the Unity engine, which is used to predict and simulate the point glue process model and generate a control signal. The control layer is used to send the control signal to the mechanical arm, so that the mechanical arm controls the movement of the needle based on the control signal.

[0023] In an embodiment, the physical layer includes an ABB mechanical arm (IRC5 controller) and a pressure sensor (0-10V analog input). The ABB IRB 2600 is equipped with a 17-bit encoder, with a sampling frequency of 1 kHz, which is used for mechanical arm motion detection, mainly collecting joint angle, end effector pose (TCP coordinate system) and other parameters of the mechanical arm, and transmitting the collected data to the virtual layer in real time (period 1 ms) through the EtherCAT protocol. The pressure sensor can be a SICK PF30 piezoelectric sensor (range 0-50N), which is used for needle pressure detection and collects the pressure of the needle.

[0024] The physical layer can adopt a communication protocol stack including ROS-Unity and TCP packet reordering, and synchronize the collected data to the virtual layer in a manner of PTPv2 clock synchronization (error < 100 μs), and ensure the data to be in the same frequency through a data compensation algorithm. Specifically, the robot arm publishes messages through a ROS driver package, and the Unity engine establishes a ROS session subscription, so as to realize the data synchronization between the physical layer and the virtual layer.

[0025] The virtual layer includes a Unity engine and a ROS-TCP-Connector plug-in. Specifically, the virtual layer establishes a virtual model of the dispensing process based on the Unity engine, that is, a dispensing virtual model, and simulates the dispensing process based on the data synchronized by the physical layer.

[0026] The virtual layer also deploys a prediction model, which adopts an LSTM network, the input layer is 12 nodes, and the hidden layer is 64 nodes. The model is trained in advance using 100,000 sets of historical pressure data of the needle, and the inference frame rate of the model is 60 FPS.

[0027] The control layer adopts ROS Noetic and a MoveIt motion planning system, and controls the motion of the robot arm according to the prediction information of the virtual layer.

[0028] Next, a dispensing control method based on a Unity engine disclosed by the embodiment of the application will be described in detail. The method is applied to the virtual layer of a dispensing control system based on a Unity engine, and can be executed by an electronic device such as a smart phone, a computer, a tablet computer, etc. Referring to the flowchart of a dispensing control method based on a Unity engine shown in Figure 1 The method mainly includes the following steps S101 to S103: Step S101: When the robot arm rocker is pressed, the real-time pressure of the needle and the distance information between the needle and the target point are acquired.

[0029] In an embodiment, in the dispensing process, the needle tube is installed on the robot arm, the needle tube is moved by the robot arm, and the glue is pushed out from the needle by applying pressure to the needle tube, so as to form an intersection on the chip. In the embodiment of the application, when the robot arm rocker is pressed, the real-time pressure of the needle can be acquired by a pressure sensor, and the distance information between the needle and the target point can be acquired by a distance sensor, or the distance information between the needle and the target point can be determined according to the movement trajectory of the robot arm.

[0030] Step S102: Based on the distance information between the needle and the target point, the real-time pressure, and the prediction model constructed in advance, prediction information is obtained, and the dispensing process is simulated based on the prediction information and the dispensing virtual model.

[0031] In one implementation, a virtual dispensing model is pre-built based on the Unity engine. This virtual model includes a virtual robotic arm, a virtual needle, and a virtual chip. After acquiring real-time pressure information from the needle and the distance between the needle and the target point, the acquired data can be synchronized to the virtual dispensing model for display. The dispensing process can then be simulated within the virtual dispensing model based on the acquired data.

[0032] Furthermore, a prediction model is pre-deployed in the virtual layer. In this embodiment of the invention, the distance information between the needle and the target point and the real-time pressure can be input into the prediction model to predict the dispensing process and obtain prediction information. The prediction information includes at least: the glue line width and the predicted movement trajectory of the needle.

[0033] Step S103: Generate a control signal based on the prediction information so that the robotic arm controls the movement of the needle based on the control signal.

[0034] In one implementation, the quality of dispensing can be determined based on the predicted glue line width. If the glue line width is too wide or too narrow, it indicates that the current glue dispensing volume from the needle is too high or too low. Therefore, the pressure applied to the glue can be adjusted, and a pressure adjustment signal can be output to the robotic arm to adjust the pressure value. Alternatively, a control signal can be generated based on the predicted motion trajectory of the needle (which could be the distance the needle moves downwards), and this control signal can be output to the robotic arm to control the needle to move according to a preset motion trajectory.

[0035] The dispensing control method based on the Unity engine provided in this embodiment of the invention can predict the dispensing process based on the Unity engine and a pre-built prediction model, and simulate the dispensing process through a dispensing virtual model. This allows for timely adjustment of the needle movement based on prediction information and policy results, thereby reducing the dispensing defect rate and damage to the chip.

[0036] In one implementation, the prediction model includes a first prediction model and a second prediction model. The first prediction model is used to predict the adhesive line width, and the second prediction model is used to predict the movement trajectory of the needle. Based on this, for the aforementioned step S102, i.e., when obtaining prediction information based on the distance information between the needle and the target point, real-time pressure, and the pre-built prediction model, the following methods can be used, including but not limited to: (1) Input the historical movement trajectory of the needle and the real-time pressure into the pre-built first prediction model to obtain the width of the adhesive line within a future preset time period.

[0037] In a specific implementation, during the movement of the mechanical arm, the movement parameters of the mechanical arm, such as the joint angle of the mechanical arm, the pose of the end effector, etc., can be obtained, and the historical motion trajectory of the needle is determined according to the movement parameters of the mechanical arm. In this embodiment, the historical motion trajectory of the needle, the pressure of the needle and the corresponding glue line width can be pre-stored as training data to train the LSTM network to obtain the first prediction model.

[0038] Based on this, when the Unity engine obtains the real-time pressure of the needle, the 10-frame historical motion trajectory and the real-time pressure can be input into the first prediction model to output the predicted value of the glue line width of the future 5 frames.

[0039] (2) input the distance information between the needle and the target point into the second prediction model constructed in advance to obtain the predicted motion trajectory of the needle.

[0040] In a specific implementation, the historical motion trajectory of the needle and the corresponding distance information between the needle and the target point can be pre-stored as training data to train the LSTM network to obtain the second prediction model. Based on this, when the Unity engine obtains the distance information between the needle and the target point, the distance information between the needle and the target point can be input into the second prediction model to output the predicted motion trajectory of the needle.

[0041] In an embodiment, the prediction model further includes a third prediction model for predicting the remaining service life of the needle. Specifically, the historical pressure information of the needle, the number of times of use and the real-time pressure are input into the third prediction model constructed in advance to obtain the remaining service life of the needle.

[0042] In a specific implementation, the third prediction model includes deformation prediction and life prediction. Specifically, first, the deformation data of the needle is predicted according to the historical pressure information and the real-time pressure of the needle, and then the service life of the needle is determined according to the deformation data of the needle, and finally the remaining service life of the needle is obtained by subtracting the number of times of use from the service life of the needle.

[0043] In an embodiment, in order to ensure the safety during the dispensing process and avoid damage to the needle and the chip, the above method further includes: performing risk warning based on the prediction information. Specifically, the risk warning based on the prediction information includes: first, controlling the movement of the needle based on the predicted motion trajectory of the needle, and obtaining the real-time motion distance of the needle during the movement of the needle; then, comparing the real-time motion distance of the needle with the pre-set distance threshold, and generating risk warning information based on the comparison result.

[0044] In specific implementation, the needle is controlled by the mechanical arm to move according to the predicted motion trajectory generated by the prediction model, and the motion process is simulated in the Unity engine. During the motion of the needle, the real-time motion distance of the needle is collected in real time, and the real-time motion distance is compared with the preset distance threshold, and risk warning information is generated according to the comparison result.

[0045] Specifically, the risk warning information includes three levels: primary, intermediate and emergency.

[0046] When the real-time motion distance of the needle is greater than or equal to the first distance threshold, the first risk warning information is generated, and the motion speed of the needle is reduced to a preset value. Specifically, the safe distance that the needle can move is determined in advance according to the distance information between the needle and the target point, and when the real-time motion distance of the needle is greater than or equal to 70% of the safe distance (i.e. the first distance threshold), it is determined as a primary risk, and the first risk warning information is generated, that is, the yellow alarm light flashes, and the motion speed of the needle is reduced by 50%.

[0047] When the real-time motion distance of the needle is greater than or equal to the second distance threshold, the second risk warning information is generated. Specifically, when the real-time motion distance of the needle is greater than or equal to 85% of the safe distance (i.e. the second distance threshold), it is determined as an intermediate risk, and the second risk warning information is generated, that is, the red alarm light flashes, and the risk is prompted through the vibration of the remote lever and the sound broadcast, and the vibration exceeds the limit for 10s.

[0048] When the real-time motion distance of the needle is greater than or equal to the third distance threshold, the third risk warning information is generated, and the motion of the needle is stopped and the air supply of the point glue is cut off. Specifically, when the real-time motion distance of the needle is greater than or equal to 95% of the safe distance (i.e. the third distance threshold), it is determined as an emergency risk, and the third risk warning information is generated, that is, the warning window is forcibly popped up, and the motion of the needle is stopped and the air supply is cut off.

[0049] Further, the risk warning based on the prediction information also includes the following ways: (1) When the remaining service life of the needle is less than the preset service life threshold, the first risk warning information is generated. Specifically, when the remaining service life of the needle is less than 200h, it is determined as a primary risk, and the first risk warning information is generated, that is, the yellow alarm light flashes, and the motion speed of the needle is reduced by 50%.

[0050] (2) The trajectory deviation value is determined based on the predicted motion trajectory of the needle, and when the trajectory deviation value exceeds the preset trajectory deviation threshold, the first risk warning information is generated. Specifically, when the trajectory deviation is greater than 0.1μm, it is determined as a primary risk, and the first risk warning information is generated, that is, the yellow alarm light flashes, and the motion speed of the needle is reduced by 50%.

[0051] (3) When the real-time pressure exceeds a preset pressure threshold, a fourth risk warning information is generated. Specifically, when the real-time pressure > 35N lasts for 200ms, an alarm is triggered.

[0052] The above method provided by the embodiment of the application builds a needle mechanical model through a Unity physical engine, calculates the mechanical distribution in real time when a joystick is pressed, and estimates the remaining service life of the needle based on accumulated deformation data. A virtual-real synchronous architecture is developed, the position deviation between the mechanical arm and the virtual needle in Unity is ≤0.5ms, and the time delay difference is eliminated; the pressure sensor updates the simulation parameters at a frequency of 1000Hz, and realizes data synchronization. A three-level warning system is constructed: visual warning, the deformation graph is displayed in real time on the Unity interface; tactile feedback, the risk level is transmitted through the vibration intensity of the joystick; sound prompt, the buzzer alarm is triggered when the predicted fracture risk > 85%. The above method can improve the dispensing width prediction accuracy to 97.3%, and at the same time reduce the mechanical arm trajectory tracking error to ±0.3mm; the dispensing repair rate is reduced by 6.8%, the pin life is extended by 30%, and the chip damage is reduced by 25%; the motor peak current is reduced by 23% through the motion trajectory smoothing algorithm; the operator intervention frequency is reduced (from 12 times per shift to 2 times), the virtual simulation system directly reuses the engineering parameters, and the training cycle is shortened by 60%.

[0053] For ease of understanding, the embodiment of the application also provides a schematic diagram of a dispensing control system based on a Unity engine, as shown in Figure 2 The system adopts a "physical-virtual-control" three-layer architecture, the physical layer includes: ABB mechanical arm (IRC5 controller) + pressure sensor (0-10V analog input); the virtual layer includes: Unity + ROS-TCP-Connector plug-in; the control layer includes: ROS Noetic + MoveIt motion planning. The mechanical arm publishes messages through the ROS driver package, and Unity establishes a ROS session subscription. The physical layer synchronizes the collected data to the virtual layer through Ether CAT networking, the virtual layer renders, synchronizes and displays data based on the obtained data, and at the same time uses a prediction model for prediction and analysis, and when a warning occurs, the alarm signal is returned to the physical layer.

[0054] It should be noted that the system provided by the embodiment of the application has the same implementation principle and technical effects as the foregoing method embodiment, and for brief description, the part not mentioned in the system embodiment can be referred to the corresponding content in the foregoing method embodiment. The specific numerical value provided in the embodiment of the application is only exemplary and is not limited herein.

[0055] The embodiment of the present application further provides an electronic device, and specifically, the electronic device comprises a processor and a storage device; the storage device stores a computer program, and the computer program performs the method according to any one of the above embodiments when the computer program is run by the processor.

[0056] Figure 3 A structural schematic diagram of an electronic device provided by the embodiment of the present application is shown in the figure, and the electronic device 100 comprises a processor 30, a memory 31, a bus 32 and a communication interface 33, the processor 30, the communication interface 33 and the memory 31 are connected through the bus 32; the processor 30 is used for executing an executable module stored in the memory 31, for example, a computer program.

[0057] The memory 31 can contain a high-speed random access memory (RAM), and can also contain a non-volatile memory, for example, at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 33 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network and the like can be used.

[0058] The bus 32 can be an ISA bus, a PCI bus or an EISA bus and the like. The bus can be divided into an address bus, a data bus, a control bus and the like. For the convenience of representation, Figure 3 Only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0059] The memory 31 is used for storing a program, and the processor 30 executes the program after receiving an execution instruction; the method executed by the device defined by the flow process disclosed in any one of the above embodiments can be applied to the processor 30 or realized by the processor 30.

[0060] The processor 30 can be an integrated circuit chip with signal processing capability. In implementation, each step of the above method can be completed by integrated logic circuit of hardware in the processor 30 or by instructions in the form of software. The processor 30 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory 31, and the processor 30 reads the information in the memory 31, and combines the hardware to complete the steps of the above method.

[0061] The computer program product of the readable storage medium provided by the embodiments of the present application comprises a computer readable storage medium storing program codes, and the program codes comprise instructions for executing the method described in the foregoing method embodiments. For specific implementation, reference can be made to the foregoing method embodiments, which will not be described here.

[0062] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0063] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some of the technical features. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A dispensing control method based on a Unity engine, characterized in that, A virtual layer applied to a dispensing control system based on a Unity engine, the virtual layer comprising a dispensing virtual model constructed based on the Unity engine; the method comprising: acquiring real-time pressure of a needle and distance information between the needle and a target point when a mechanical arm joystick is pressed; based on the distance information between the needle and the target point, the real-time pressure and a pre-constructed prediction model, obtaining prediction information, and based on the prediction information and the dispensing virtual model, simulating a dispensing process; wherein the prediction information at least includes: glue line width and predicted motion trajectory of the needle; generating a control signal based on the prediction information, so that the mechanical arm controls the motion of the needle based on the control signal.

2. The method of claim 1, wherein, Based on the distance information between the needle and the target point, the real-time pressure and the pre-constructed prediction model, obtaining prediction information, comprising: inputting the historical motion trajectory of the needle and the real-time pressure into a pre-constructed first prediction model to obtain the glue line width in a future preset time period; inputting the distance information between the needle and the target point into a pre-constructed second prediction model to obtain the predicted motion trajectory of the needle.

3. The method of claim 1, wherein, Based on the distance information between the needle and the target point, the real-time pressure and the pre-constructed prediction model, obtaining prediction information, further comprising: inputting the historical pressure information of the needle, the number of times used and the real-time pressure into a pre-constructed third prediction model to obtain the remaining service life of the needle.

4. The method of claim 1, wherein, Further comprising: based on the prediction information, risk warning.

5. The method of claim 4, wherein, Based on the prediction information, risk warning, comprising: based on the predicted motion trajectory of the needle, controlling the motion of the needle, and acquiring the real-time motion distance of the needle during the motion of the needle; comparing the real-time motion distance of the needle with a pre-set distance threshold, and generating risk warning information based on the comparison result.

6. The method of claim 5, wherein, Based on the comparison result, generating risk warning information, comprising: when the real-time motion distance of the needle is greater than or equal to a first distance threshold, generating first risk warning information, and reducing the motion speed of the needle to a preset value; when the real-time motion distance of the needle is greater than or equal to a second distance threshold, generating second risk warning information; when the real-time motion distance of the needle is greater than or equal to a third distance threshold, generating third risk warning information, and stopping the motion of the needle and cutting off the air supply of dispensing.

7. The method of claim 4, wherein, Based on the prediction information, risk warning, further comprising: when the remaining service life of the needle is less than a preset service life threshold, generating first risk warning information; determining a trajectory deviation value based on the predicted motion trajectory of the needle, and generating first risk warning information when the trajectory deviation value exceeds a preset trajectory deviation threshold; when the real-time pressure exceeds a preset pressure threshold, generating fourth risk warning information.

8. A glue dispensing control system based on Unity engine, characterized in that, Comprising: physical layer, virtual layer and control layer; The physical layer comprises a mechanical arm and a pressure sensor, configured to collect real-time pressure of a needle and distance information between the needle and a target point, and send the real-time pressure and the distance information between the needle and the target point to the virtual layer; The virtual layer comprises a dispensing virtual model constructed based on a Unity engine, configured to predict and simulate a dispensing process by using the dispensing control method based on the Unity engine according to any one of claims 1 to 7, and generate a control signal; The control layer is configured to send the control signal to the mechanical arm, so that the mechanical arm controls movement of the needle based on the control signal.

9. An electronic device, comprising: A processor and a memory are included, the memory stores computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement steps of the method according to any one of claims 1 to 7.

Images